> ## Documentation Index
> Fetch the complete documentation index at: https://honeydew.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# MCP Server

## What is MCP?

[Model Context Protocol (MCP)](https://modelcontextprotocol.io/)
is an open-source standard for securely connecting
AI applications to external systems and tools.
Honeydew provides an MCP server that connects
your AI coding assistant to the Honeydew Semantic Layer.

### When to use

* Discover and explore your warehouse tables,
  schemas, and semantic model definitions
* Build and maintain your semantic model
  through natural conversation
* Query your data with natural language
  from any MCP-compatible assistant

## Installation

### Server URL

Honeydew exposes the MCP Server API at
`https://mcp.honeydew.cloud/mcp`

<Note>
  If your organization uses a custom Honeydew hostname,
  replace the default URL with your tenant hostname.
  You can find the hostname in the Honeydew UI under
  **Settings > MCP Server**.
</Note>

### Authentication

There are two ways to authenticate with
the Honeydew MCP Server:
**OAuth** or **HTTP Basic authentication**.

**OAuth Authentication (recommended)**

Most clients support OAuth authentication.
When you first connect, you'll be prompted to:

1. Log in with your Honeydew account
2. Accept the OAuth authorization

The client then securely provides an access token for subsequent requests.

**HTTP Basic Authentication**

The MCP Server in HTTP Basic authentication mode
requires an [API Key](/access-control/api-keys)
for authentication.

You need to provide a Base64-encoded string
of your API Key and API Secret
in the format `API_KEY:API_SECRET`.

<Tip>
  If creating a new API Key for MCP Server access,
  you can copy the Base64-encoded string
  from the Honeydew Studio UI at the time of creation.
</Tip>

You can use the following command
to generate the Base64-encoded string:

<Tabs>
  <Tab title="MacOS">
    ```bash theme={null}
    echo -n '<API_KEY>:<API_SECRET>' | base64
    ```
  </Tab>

  <Tab title="Windows">
    Use PowerShell:

    ```powershell theme={null}
    [Convert]::ToBase64String(
      [Text.Encoding]::UTF8.GetBytes(
        "<API_KEY>:<API_SECRET>"
      )
    )
    ```
  </Tab>
</Tabs>

Provide the encoded string
in the `Authorization` header as follows:

`Authorization: Basic <YOUR_BASE64_ENCODED_API_KEY_AND_SECRET>`

### Configuration

The workspace and branch are set at the session level
using the [`list_workspaces`](#list_workspaces),
[`list_workspace_branches`](#list_workspace_branches)
and [`set_session_workspace_and_branch`](#set_session_workspace_and_branch)
tools. You can also create new branches with
[`create_workspace_branch`](#create_workspace_branch).
Call these tools from your AI assistant
after connecting to the MCP server.

You can optionally provide these headers in your MCP server configuration:

* `Workspace`: Pin the workspace for all requests (optional)
* `Branch`: Pin a specific workspace branch for all requests (optional, defaults to `prod` if workspace is set)
* `Honeydew-Client`: Identify the MCP client (optional,
  auto-detected from the connected tool).
  Pass this header to provide a specific client identifier.
* `ReadonlyToolsOnly`: Set to `true` to expose only read-only tools (optional)

<Note>
  The MCP server uses the `Mcp-Session-Id` response header
  to maintain session state, including the active workspace and branch.
  See the [MCP session management specification](https://modelcontextprotocol.io/specification/2025-06-18/basic/transports#session-management)
  for details.
</Note>

## Supported Clients

### Claude Code CLI

<Accordion title="Setup instructions">
  #### Plugin Installation

  Honeydew provides a
  [plugins repository](https://github.com/honeydew-ai/honeydew-ai-coding-agents-plugins)
  with skills and tools for building semantic models
  and analyzing data through natural conversation.
  Installing the plugin sets up the Honeydew MCP servers automatically.

  Launch Claude Code with `claude`, then add the marketplace:

  ```
  /plugin marketplace add honeydew-ai/honeydew-ai-coding-agents-plugins
  ```

  Then install the Honeydew plugin from the marketplace:

  ```
  /plugin install honeydew-ai@honeydew-ai-claude-plugins
  ```

  Then reload plugins to activate:

  ```
  /reload-plugins
  ```

  **Updating plugins**

  To update the Honeydew marketplace plugins, launch Claude Code with `claude`, then:

  1. Write `/plugin` and select **Marketplaces** in the selector at the top
  2. Select `honeydew-ai-coding-agents-plugins`
  3. Click **Update marketplace**

  To receive updates automatically, select **Enable auto-update**
  in the marketplace settings.

  #### MCP Setup

  Use this section if your organization uses a custom Honeydew endpoint,
  or if you prefer to configure the MCP servers without installing the plugin.
  Disable the Honeydew MCP connection added by the plugin, then add your
  custom endpoint using the instructions below.

  Honeydew provides two MCP servers:

  * **Honeydew MCP** — connects Claude Code to the Honeydew Semantic Layer
    for model exploration, data querying, and model management
  * **Honeydew Documentation MCP** — gives Claude Code access to Honeydew
    documentation. No authentication required. Add it with:

    ```bash theme={null}
    claude mcp add --transport http honeydew-docs \
        https://honeydew.ai/docs/mcp
    ```

  Use one of the following methods to add the Honeydew MCP server:

  <Note>
    If your organization uses a custom Honeydew hostname,
    replace `https://mcp.honeydew.cloud/mcp` with your tenant hostname.
    You can find the hostname in **Settings > MCP Server** in Honeydew Studio.
  </Note>

  <Tabs>
    <Tab title="Command line">
      <Tabs>
        <Tab title="OAuth (recommended)">
          ```bash theme={null}
          claude mcp add --transport http honeydew \
              https://mcp.honeydew.cloud/mcp
          ```

          Launch Claude Code with `claude`.
          You'll be prompted to authenticate with OAuth to Honeydew.
        </Tab>

        <Tab title="API Key">
          ```bash theme={null}
          claude mcp add --transport http honeydew \
              https://mcp.honeydew.cloud/mcp \
              --header "Authorization: Basic <YOUR_BASE64_ENCODED_API_KEY_AND_SECRET>"
          ```
        </Tab>
      </Tabs>
    </Tab>

    <Tab title="JSON configuration">
      Save the following to `honeydew-mcp.json`:

      <Tabs>
        <Tab title="OAuth (recommended)">
          ```json theme={null}
          {
            "type": "http",
            "url": "https://mcp.honeydew.cloud/mcp"
          }
          ```

          Then register it with:

          ```bash theme={null}
          claude mcp add honeydew ./honeydew-mcp.json
          ```

          Launch Claude Code with `claude`.
          You'll be prompted to authenticate with OAuth to Honeydew.
        </Tab>

        <Tab title="API Key">
          ```json theme={null}
          {
            "type": "http",
            "url": "https://mcp.honeydew.cloud/mcp",
            "headers": {
              "Authorization": "Basic <YOUR_BASE64_ENCODED_API_KEY_AND_SECRET>"
            }
          }
          ```

          Then register it with:

          ```bash theme={null}
          claude mcp add honeydew ./honeydew-mcp.json
          ```
        </Tab>
      </Tabs>
    </Tab>

    <Tab title=".mcp.json">
      Add the following to your `.mcp.json` file:

      <Tabs>
        <Tab title="OAuth (recommended)">
          ```json theme={null}
          {
            "mcpServers": {
              "honeydew": {
                "type": "http",
                "url": "https://mcp.honeydew.cloud/mcp"
              }
            }
          }
          ```

          Launch Claude Code with `claude`.
          You'll be prompted to authenticate with OAuth to Honeydew.
        </Tab>

        <Tab title="API Key">
          ```json theme={null}
          {
            "mcpServers": {
              "honeydew": {
                "type": "http",
                "url": "https://mcp.honeydew.cloud/mcp",
                "headers": {
                  "Authorization": "Basic <YOUR_BASE64_ENCODED_API_KEY_AND_SECRET>"
                }
              }
            }
          }
          ```
        </Tab>
      </Tabs>
    </Tab>
  </Tabs>

  <Tip>
    **Using environment variables for API Key authentication**

    To avoid storing sensitive values directly in configuration files,
    Claude Code supports
    [environment variable expansion](https://code.claude.com/docs/en/mcp#environment-variable-expansion-in-mcp-json)
    using the `${VAR_NAME}` syntax.

    Set the `HONEYDEW_API_KEY` environment variable,
    then reference it in your configuration:

    ```bash theme={null}
    claude mcp add --transport http honeydew \
        https://mcp.honeydew.cloud/mcp \
        --header "Authorization: Basic ${HONEYDEW_API_KEY}"
    ```

    Claude Code resolves `${VAR_NAME}` references
    at runtime from your environment.
  </Tip>

  #### Removing the MCP server

  To remove the Honeydew MCP server:

  ```bash theme={null}
  claude mcp remove honeydew
  ```

  To remove the Honeydew Documentation MCP server:

  ```bash theme={null}
  claude mcp remove honeydew-docs
  ```
</Accordion>

### Claude Desktop

<Accordion title="Setup instructions">
  #### Plugin Installation

  Honeydew provides a
  [plugins repository](https://github.com/honeydew-ai/honeydew-ai-coding-agents-plugins)
  with skills and tools for building semantic models
  and analyzing data through natural conversation.
  Installing the plugin sets up the Honeydew MCP servers automatically.

  1. Go to **Settings** -> **Customize**
  2. Click **Browse Plugins**
  3. Go to the **Personal** tab
  4. Click the **+** icon
     and choose **Add marketplace from GitHub**
  5. Enter
     `honeydew-ai/honeydew-ai-coding-agents-plugins`
     in the input box
  6. The **Honeydew AI** plugin appears. Install it.

  #### MCP Setup

  Use this section if your organization uses a custom Honeydew endpoint,
  or if you prefer to configure the MCP servers without installing the plugin.
  Disable the Honeydew MCP connection added by the plugin, then add your
  custom endpoint using the instructions below.

  Honeydew provides two MCP servers:

  * **Honeydew MCP** — connects Claude Desktop to the Honeydew Semantic Layer
    for model exploration, data querying, and model management
  * **Honeydew Documentation MCP** — gives Claude Desktop access to Honeydew
    documentation. No authentication required.

  **Claude Code mode**

  When using Claude Desktop in Claude Code mode,
  follow the [Claude Code CLI](#claude-code-cli) instructions instead.

  <Note>
    If your organization uses a custom Honeydew hostname,
    replace `https://mcp.honeydew.cloud/mcp` with your tenant hostname.
    You can find the hostname in **Settings > MCP Server** in Honeydew Studio.
  </Note>

  To add the Honeydew MCP in Cowork mode:

  1. Go to **Settings** -> **Connectors** -> **Add custom connector**
  2. Enter `honeydew` in the **Name** field
  3. Enter `https://mcp.honeydew.cloud/mcp` in the **Remote MCP server URL** field
  4. Click **Add**

  You'll be prompted to authenticate with OAuth to Honeydew when first connecting.

  To add the Honeydew Documentation MCP:

  1. Go to **Settings** -> **Connectors** -> **Add custom connector**
  2. Enter `honeydew-docs` in the **Name** field
  3. Enter `https://honeydew.ai/docs/mcp` in the **Remote MCP server URL** field
  4. Click **Add**

  #### Removing the MCP server

  To remove the Honeydew MCP server in Cowork mode:

  1. Go to **Settings** -> **Connectors**
  2. Find the `honeydew` connector and click the delete icon

  To remove the Honeydew Documentation MCP server:

  1. Go to **Settings** -> **Connectors**
  2. Find the `honeydew-docs` connector and click the delete icon
</Accordion>

### Claude.ai

<Accordion title="Setup instructions">
  #### Plugin Installation

  Honeydew provides a
  [plugins repository](https://github.com/honeydew-ai/honeydew-ai-coding-agents-plugins)
  with skills and tools for building semantic models
  and analyzing data through natural conversation.
  Installing the plugin sets up both the Honeydew MCP server and the
  Honeydew Documentation MCP server automatically.

  1. Download the plugin zip:
     [honeydew-ai-claude.zip](https://github.com/honeydew-ai/honeydew-ai-coding-agents-plugins/releases/latest/download/honeydew-ai-claude.zip)
  2. In Claude.ai, go to **Settings** -> **Plugins** -> **Add plugin** -> **Upload zip**
  3. Upload the zip — the plugin appears in your private marketplace

  #### MCP Setup

  Use this section if your organization uses a custom Honeydew endpoint,
  or if you prefer to configure the MCP servers without installing the plugin.
  Remove the Honeydew MCP connector added by the plugin, then add your
  custom endpoint using the instructions below.

  Honeydew provides two MCP servers:

  * **Honeydew MCP** — connects Claude.ai to the Honeydew Semantic Layer
    for model exploration, data querying, and model management
  * **Honeydew Documentation MCP** — gives Claude.ai access to Honeydew
    documentation. No authentication required.

  <Note>
    If your organization uses a custom Honeydew hostname,
    replace `https://mcp.honeydew.cloud/mcp` with your tenant hostname.
    You can find the hostname in **Settings > MCP Server** in Honeydew Studio.
  </Note>

  To add the Honeydew MCP server:

  1. Go to **Settings** -> **Connectors** -> **Add custom connector**
  2. Enter `honeydew` in the **Name** field
  3. Enter `https://mcp.honeydew.cloud/mcp` in the **Remote MCP server URL** field
  4. Click **Add**

  You'll be prompted to authenticate with OAuth to Honeydew when first connecting.

  To add the Honeydew Documentation MCP:

  1. Go to **Settings** -> **Connectors** -> **Add custom connector**
  2. Enter `honeydew-docs` in the **Name** field
  3. Enter `https://honeydew.ai/docs/mcp` in the **Remote MCP server URL** field
  4. Click **Add**

  #### Removing the MCP server

  To remove the Honeydew MCP server:

  1. Go to **Settings** -> **Connectors**
  2. Find the `honeydew` connector and click the delete icon

  To remove the Honeydew Documentation MCP server:

  1. Go to **Settings** -> **Connectors**
  2. Find the `honeydew-docs` connector and click the delete icon
</Accordion>

### Cortex Code CLI

<Accordion title="Setup instructions">
  #### Plugin Installation

  Honeydew provides a
  [plugins repository](https://github.com/honeydew-ai/honeydew-ai-coding-agents-plugins)
  with skills and tools for building semantic models
  and analyzing data through natural conversation.
  Installing the plugin sets up the Honeydew MCP servers automatically.

  Launch Cortex Code CLI with `cortex`, then install the plugin:

  ```
  /plugin install honeydew-ai/honeydew-ai-coding-agents-plugins
  ```

  #### MCP Setup

  Use this section if your organization uses a custom Honeydew endpoint,
  or if you prefer to configure the MCP servers without installing the plugin.
  Disable the Honeydew MCP connection added by the plugin, then add your
  custom endpoint using the instructions below.

  Honeydew provides two MCP servers:

  * **Honeydew MCP** — connects Cortex Code CLI to the Honeydew Semantic Layer
    for model exploration, data querying, and model management
  * **Honeydew Documentation MCP** — gives Cortex Code CLI access to Honeydew
    documentation. No authentication required. Add it with:

    ```bash theme={null}
    cortex mcp add honeydew-docs \
        https://honeydew.ai/docs/mcp \
        --type http
    ```

  <Note>
    If your organization uses a custom Honeydew hostname,
    replace `https://mcp.honeydew.cloud/mcp` with your tenant hostname.
    You can find the hostname in **Settings > MCP Server** in Honeydew Studio.
  </Note>

  <Tabs>
    <Tab title="Command line">
      <Tabs>
        <Tab title="OAuth (recommended)">
          ```bash theme={null}
          cortex mcp add honeydew \
              https://mcp.honeydew.cloud/mcp \
              --type http
          ```

          Launch Cortex Code CLI with `cortex`.
          You'll be prompted to authenticate
          with OAuth to Honeydew.
        </Tab>

        <Tab title="API Key">
          ```bash theme={null}
          cortex mcp add honeydew \
              https://mcp.honeydew.cloud/mcp \
              --type http \
              -H "Authorization: Basic <YOUR_BASE64_ENCODED_API_KEY_AND_SECRET>"
          ```
        </Tab>
      </Tabs>
    </Tab>

    <Tab title="JSON configuration">
      Save the following to `honeydew-mcp.json`:

      <Tabs>
        <Tab title="OAuth (recommended)">
          ```json theme={null}
          {
            "type": "http",
            "url": "https://mcp.honeydew.cloud/mcp"
          }
          ```

          Then register it with:

          ```bash theme={null}
          cortex mcp add honeydew ./honeydew-mcp.json --type http
          ```

          Launch Cortex Code CLI with `cortex`.
          You'll be prompted to authenticate
          with OAuth to Honeydew.
        </Tab>

        <Tab title="API Key">
          ```json theme={null}
          {
            "type": "http",
            "url": "https://mcp.honeydew.cloud/mcp",
            "headers": {
              "Authorization": "Basic <YOUR_BASE64_ENCODED_API_KEY_AND_SECRET>"
            }
          }
          ```

          Then register it with:

          ```bash theme={null}
          cortex mcp add honeydew ./honeydew-mcp.json --type http
          ```
        </Tab>
      </Tabs>
    </Tab>

    <Tab title="mcp.json">
      Add the following to
      `~/.snowflake/cortex/mcp.json`:

      <Tabs>
        <Tab title="OAuth (recommended)">
          ```json theme={null}
          {
            "mcpServers": {
              "honeydew": {
                "type": "http",
                "url": "https://mcp.honeydew.cloud/mcp"
              }
            }
          }
          ```

          Launch Cortex Code CLI with `cortex`.
          You'll be prompted to authenticate
          with OAuth to Honeydew.
        </Tab>

        <Tab title="API Key">
          ```json theme={null}
          {
            "mcpServers": {
              "honeydew": {
                "type": "http",
                "url": "https://mcp.honeydew.cloud/mcp",
                "headers": {
                  "Authorization": "Basic <YOUR_BASE64_ENCODED_API_KEY_AND_SECRET>"
                }
              }
            }
          }
          ```
        </Tab>
      </Tabs>
    </Tab>
  </Tabs>

  #### Removing the MCP server

  To remove the Honeydew MCP server:

  ```bash theme={null}
  cortex mcp remove honeydew
  ```

  To remove the Honeydew Documentation MCP server:

  ```bash theme={null}
  cortex mcp remove honeydew-docs
  ```
</Accordion>

### Cortex Code Desktop

<Accordion title="Setup instructions">
  #### Plugin Installation

  Honeydew provides a
  [plugins repository](https://github.com/honeydew-ai/honeydew-ai-coding-agents-plugins)
  with skills and tools for building semantic models
  and analyzing data through natural conversation.
  Installing the plugin sets up the Honeydew MCP servers automatically.

  1. Go to **Settings** -> **Plugins**
  2. Click **Add Plugin**, select **Add from GitHub**, and paste the
     Honeydew plugin repository: `honeydew-ai/honeydew-ai-coding-agents-plugins`
  3. Follow the flow and approve the steps in **GitHub Plugin Installer Setup**

  #### MCP Setup

  Use this section if your organization uses a custom Honeydew endpoint,
  or if you prefer to configure the MCP servers without installing the plugin.
  Disable the Honeydew MCP connection added by the plugin, then add your
  custom endpoint using the instructions below.

  Honeydew provides two MCP servers:

  * **Honeydew MCP** — connects Cortex Code Desktop to the Honeydew Semantic Layer
    for model exploration, data querying, and model management
  * **Honeydew Documentation MCP** — gives Cortex Code Desktop access to Honeydew
    documentation. No authentication required.

  To add a server, go to **MCP** -> **New**, choose a **Configuration Scope**
  (for example, `~/.snowflake/cortex/mcp.json` for Global), fill in the form,
  then click **Save**. Use the **Form** or **JSON** tab to enter the configuration.

  <Note>
    If your organization uses a custom Honeydew hostname,
    replace `https://mcp.honeydew.cloud/mcp` with your tenant hostname.
    You can find the hostname in **Settings > MCP Server** in Honeydew Studio.
  </Note>

  Add the **Honeydew MCP** server:

  <Tabs>
    <Tab title="Form">
      <Tabs>
        <Tab title="OAuth (recommended)">
          1. **Server Name**: `honeydew`
          2. **Server Type**: **Remote (HTTP)**
          3. **Server URL**: `https://mcp.honeydew.cloud/mcp`
          4. Click **Save**

          You'll be prompted to authenticate with OAuth to Honeydew
          when first connecting.
        </Tab>

        <Tab title="API Key">
          1. **Server Name**: `honeydew`
          2. **Server Type**: **Remote (HTTP)**
          3. **Server URL**: `https://mcp.honeydew.cloud/mcp`
          4. Under **Headers**, click **Add Header** and set the name to
             `Authorization` and the value to
             `Basic <YOUR_BASE64_ENCODED_API_KEY_AND_SECRET>`
          5. Click **Save**
        </Tab>
      </Tabs>
    </Tab>

    <Tab title="JSON">
      Switch to the **JSON** tab and paste the configuration:

      <Tabs>
        <Tab title="OAuth (recommended)">
          ```json theme={null}
          {
            "honeydew": {
              "type": "http",
              "url": "https://mcp.honeydew.cloud/mcp"
            }
          }
          ```

          You'll be prompted to authenticate with OAuth to Honeydew
          when first connecting.
        </Tab>

        <Tab title="API Key">
          ```json theme={null}
          {
            "honeydew": {
              "type": "http",
              "url": "https://mcp.honeydew.cloud/mcp",
              "headers": {
                "Authorization": "Basic <YOUR_BASE64_ENCODED_API_KEY_AND_SECRET>"
              }
            }
          }
          ```
        </Tab>
      </Tabs>
    </Tab>
  </Tabs>

  Add the **Honeydew Documentation MCP** server the same way, using **Server Name**
  `honeydew-docs`, **Server Type** **Remote (HTTP)**, and **Server URL**
  `https://honeydew.ai/docs/mcp`. No authentication is required.

  #### Removing the MCP server

  To remove a server, go to **MCP**, find the `honeydew` (or `honeydew-docs`)
  server, and remove it.
</Accordion>

### Cursor

<Accordion title="Setup instructions">
  #### Plugin Installation

  Honeydew provides a
  [plugins repository](https://github.com/honeydew-ai/honeydew-ai-coding-agents-plugins)
  with skills and tools for building semantic models
  and analyzing data through natural conversation.
  Installing the plugin sets up the Honeydew MCP servers automatically.

  1. In your team or organization settings,
     go to [cursor.com/dashboard/plugins](https://cursor.com/dashboard/plugins)
     (or click **Plugins** on the left side menu)
  2. Scroll down to **Team Marketplaces** and either click an existing Marketplace,
     or click **Add Marketplace** to create a new one.
     If creating a new one, enter a name and create it.
  3. Within the Marketplace, click **Add Plugin**,
     paste the Honeydew plugin GitHub repository path:
     `https://github.com/honeydew-ai/honeydew-ai-coding-agents-plugins`
     and click **Add 1 plugin**
  4. Optionally, enable **auto-refresh** in the Marketplace page
     so the plugin updates automatically when new versions are released.
  5. Go back to the plugins page
     ([cursor.com/dashboard/plugins](https://cursor.com/dashboard/plugins)),
     search for the Honeydew plugin, and click **Add**

  #### MCP Setup

  Use this section if your organization uses a custom Honeydew endpoint,
  or if you prefer to configure the MCP servers without installing the plugin.
  Disable the Honeydew MCP connection added by the plugin, then add your
  custom endpoint using the instructions below.

  Honeydew provides two MCP servers:

  * **Honeydew MCP** — connects Cursor to the Honeydew Semantic Layer
    for model exploration, data querying, and model management
  * **Honeydew Documentation MCP** — gives Cursor access to Honeydew
    documentation. No authentication required.

  <Note>
    If your organization uses a custom Honeydew hostname,
    replace `https://mcp.honeydew.cloud/mcp` with your tenant hostname.
    You can find the hostname in **Settings > MCP Server** in Honeydew Studio.
  </Note>

  To add the Honeydew MCP:

  1. Open the Cursor application

  2. Go to **Settings** -> **Cursor Settings**
     -> **Tools & MCP**

  3. Click **New MCP Server**

  4. Add the following configuration:

       <Tabs>
         <Tab title="OAuth (recommended)">
           ```json theme={null}
           {
             "name": "honeydew",
             "type": "http",
             "url": "https://mcp.honeydew.cloud/mcp"
           }
           ```
         </Tab>

         <Tab title="API Key">
           ```json theme={null}
           {
             "name": "honeydew",
             "type": "http",
             "url": "https://mcp.honeydew.cloud/mcp",
             "headers": {
               "Authorization": "Basic <YOUR_BASE64_ENCODED_API_KEY_AND_SECRET>"
             }
           }
           ```
         </Tab>
       </Tabs>

  5. Click **Save**

  To add the Honeydew Documentation MCP:

  1. Go to **Settings** -> **Cursor Settings**
     -> **Tools & MCP**
  2. Click **New MCP Server**
  3. Add the following configuration:
     ```json theme={null}
     {
       "name": "honeydew-docs",
       "type": "http",
       "url": "https://honeydew.ai/docs/mcp"
     }
     ```
  4. Click **Save**

  #### Removing the MCP server

  To remove the Honeydew MCP server:

  1. Go to **Settings** -> **Cursor Settings** -> **Tools & MCP**
  2. Find `honeydew` in the list and click the delete icon

  To remove the Honeydew Documentation MCP server:

  1. Go to **Settings** -> **Cursor Settings** -> **Tools & MCP**
  2. Find `honeydew-docs` in the list and click the delete icon
</Accordion>

### Databricks Genie Code

<Accordion title="Setup instructions">
  <Note>
    MCP servers are only supported in Genie Code Agent mode.
    For more details, see the
    [Databricks MCP documentation](https://docs.databricks.com/aws/en/generative-ai/mcp/).
  </Note>

  **Prerequisites:**

  * Genie Code enabled in your Databricks workspace
  * `CREATE CONNECTION` privilege on the Unity Catalog metastore

  <Steps>
    <Step title="Create the HTTP connection">
      <Tabs>
        <Tab title="Databricks UI">
          1. Navigate to **Catalog** → **Connections** → **Create a connection**
          2. On the **Connection basics** screen:
             * Set **Connection name** to `honeydew-mcp`
             * Set **Connection type** to **HTTP**
             * Set **Auth type** to **Dynamic Client Registration**
             * Click **Next**
          3. On the **Authentication** screen:
             * Set **Host** to `https://mcp.honeydew.cloud`
             * Leave **Port** as `443`
             * Set **OAuth scope** to `openid`
             * Click **Next**
          4. On the **Connection details** screen:
             * Check **Is MCP connection**
             * Set **Base path** to `/mcp`
             * Click **Create connection**
        </Tab>

        <Tab title="SQL">
          Run the following SQL in a Databricks notebook or SQL editor:

          ```sql theme={null}
          CREATE OR REPLACE CONNECTION `honeydew-mcp` TYPE HTTP
          OPTIONS (
            host 'https://mcp.honeydew.cloud',
            base_path '/mcp',
            is_mcp_connection 'true',
            oauth_scope 'openid'
          );

          DESCRIBE CONNECTION `honeydew-mcp`;
          ```
        </Tab>
      </Tabs>

      <Note>
        If your organization uses a custom Honeydew hostname, replace
        `https://mcp.honeydew.cloud` with your tenant hostname.
        You can find your hostname in **Settings > MCP Server** in Honeydew Studio.
      </Note>
    </Step>

    <Step title="Log in to the connection">
      Navigate to **Catalog** → **Connections** → `honeydew-mcp`
      and click **Login** in the upper right corner
      to authenticate and verify the connection.
    </Step>

    <Step title="Grant connection access">
      Grant the `USE CONNECTION` privilege to any users or roles
      that need access to the Honeydew MCP server:

      ```sql theme={null}
      GRANT USE CONNECTION ON CONNECTION `honeydew-mcp` TO <user-or-role>;
      ```
    </Step>

    <Step title="Add the MCP server in Genie Code">
      1. Open Genie Code and click the gear icon
      2. Navigate to **MCP Servers** → **Add Server**
      3. Select **External MCP server**
      4. Choose the `honeydew-mcp` connection you created
      5. Log in to the connection when prompted
      6. Click **Save**

      <Note>
        Databricks limits MCP to 20 tools across all configured servers.
        If you need to adjust which Honeydew tools are available,
        use the Genie Code MCP settings to enable or disable specific tools.
      </Note>
    </Step>
  </Steps>

  #### Removing the MCP server

  To remove the Honeydew MCP server from Genie Code:

  1. Open Genie Code and click the gear icon
  2. Navigate to **MCP Servers**
  3. Find `honeydew-mcp` and click **Remove**

  To also remove the underlying Unity Catalog connection,
  run the following SQL:

  ```sql theme={null}
  DROP CONNECTION `honeydew-mcp`;
  ```
</Accordion>

### Devin

<Accordion title="Setup instructions">
  #### MCP Server

  [Devin](https://devin.ai) connects to remote MCP servers through its
  [MCP Marketplace](https://docs.devin.ai/work-with-devin/mcp).

  <Note>
    If your organization uses a custom Honeydew hostname,
    replace `https://mcp.honeydew.cloud/mcp` with your tenant hostname.
    You can find the hostname in **Settings > MCP Server** in Honeydew Studio.
  </Note>

  To add the Honeydew MCP server:

  1. Go to **Settings** -> **Connections** -> **MCP servers**

  2. Click **Add a custom MCP**

  3. Enter `honeydew` in the **Server Name** field

  4. Optionally add an icon and a **Short Description**

  5. Choose **HTTP** as the transport type

  6. Enter `https://mcp.honeydew.cloud/mcp` in the **Server URL** field

  7. Configure authentication:

       <Tabs>
         <Tab title="OAuth (recommended)">
           Select **OAuth** as the authentication method.
           Devin prompts you to authenticate with Honeydew during the first session.
         </Tab>

         <Tab title="API Key">
           Select **Auth Header** as the authentication method.
           Leave the header key as `Authorization` and set the value to
           `Basic <YOUR_BASE64_ENCODED_API_KEY_AND_SECRET>`
           (see [Authentication](#authentication)).
         </Tab>
       </Tabs>

  8. Click **Save**, then click **Test listing tools** to verify the connection

  #### Honeydew Documentation MCP

  Give Devin access to the Honeydew documentation
  through a separate MCP server.
  No authentication is required.

  1. Go to **Settings** -> **Connections** -> **MCP servers**
  2. Click **Add a custom MCP**
  3. Enter `honeydew-docs` in the **Server Name** field
  4. Choose **HTTP** as the transport type
  5. Enter `https://honeydew.ai/docs/mcp` in the **Server URL** field
  6. Set the authentication method to **None**
  7. Click **Save**

  #### Removing the MCP server

  To remove the Honeydew MCP server:

  1. Go to **Settings** -> **Connections** -> **MCP servers**
  2. Find the `honeydew` server and remove it

  To remove the Honeydew Documentation MCP server:

  1. Go to **Settings** -> **Connections** -> **MCP servers**
  2. Find the `honeydew-docs` server and remove it
</Accordion>

### GitHub Copilot CLI

<Accordion title="Setup instructions">
  #### MCP Server

  <Note>
    If your organization uses a custom Honeydew hostname,
    replace `https://mcp.honeydew.cloud/mcp` with your tenant hostname.
    You can find the hostname in **Settings > MCP Server** in Honeydew Studio.
  </Note>

  1. Launch GitHub Copilot CLI with `copilot`

  2. Type `/mcp add` to open the server configuration form

  3. Fill in the following fields:

     * **Name**: `honeydew`
     * **Type**: `http`
     * **URL**: `https://mcp.honeydew.cloud/mcp`
     * **HTTP Headers**:

       <Tabs>
         <Tab title="OAuth (recommended)">
           No additional headers are needed for OAuth.
         </Tab>

         <Tab title="API Key">
           ```json theme={null}
           {
             "Authorization": "Basic <YOUR_BASE64_ENCODED_API_KEY_AND_SECRET>"
           }
           ```
         </Tab>
       </Tabs>

  4. Press `Ctrl+S` to save

  Use `/mcp show` to verify the server is connected.

  #### AI Coding Agent Plugins

  Honeydew provides a
  [plugins repository](https://github.com/honeydew-ai/honeydew-ai-coding-agents-plugins)
  with skills and tools for building semantic models
  and analyzing data through natural conversation.

  Add the marketplace to Copilot CLI:

  ```
  /plugin marketplace add honeydew-ai/honeydew-ai-coding-agents-plugins
  ```

  Then install the Honeydew plugin from the marketplace:

  ```
  /plugin install honeydew-ai@honeydew-ai-github-copilot-plugins
  ```

  #### Honeydew Documentation MCP

  Give Copilot CLI access to the Honeydew documentation through a separate MCP server.
  No authentication is required.

  1. Launch GitHub Copilot CLI with `copilot`
  2. Type `/mcp add` to open the server configuration form
  3. Fill in the following fields:
     * **Name**: `honeydew-docs`
     * **Type**: `http`
     * **URL**: `https://honeydew.ai/docs/mcp`
  4. Press `Ctrl+S` to save

  #### Removing the MCP server

  To remove the Honeydew MCP server,
  launch GitHub Copilot CLI with `copilot`, then type:

  ```
  /mcp remove honeydew
  ```

  To remove the Honeydew Documentation MCP server:

  ```
  /mcp remove honeydew-docs
  ```
</Accordion>

### Gemini CLI

<Accordion title="Setup instructions">
  #### Extension Installation

  Honeydew provides a
  [plugins repository](https://github.com/honeydew-ai/honeydew-ai-coding-agents-plugins)
  with skills and tools for building semantic models
  and analyzing data through natural conversation.
  Installing the extension sets up the Honeydew MCP servers automatically.

  Run the following command to install the Honeydew extension:

  ```bash theme={null}
  gemini extensions install \
      https://github.com/honeydew-ai/honeydew-ai-coding-agents-plugins \
      --auto-update
  ```

  The `--auto-update` flag keeps the extension updated automatically.

  #### MCP Setup

  Use this section if your organization uses a custom Honeydew endpoint,
  or if you prefer to configure the MCP servers without installing the extension.
  Disable the Honeydew MCP connection added by the extension, then add your
  custom endpoint using the instructions below.

  Honeydew provides two MCP servers:

  * **Honeydew MCP** — connects Gemini CLI to the Honeydew Semantic Layer
    for model exploration, data querying, and model management
  * **Honeydew Documentation MCP** — gives Gemini CLI access to Honeydew
    documentation. No authentication required. Add it with:

    ```bash theme={null}
    gemini mcp add --transport http honeydew-docs \
        https://honeydew.ai/docs/mcp
    ```

  <Note>
    If your organization uses a custom Honeydew hostname,
    replace `https://mcp.honeydew.cloud/mcp` with your tenant hostname.
    You can find the hostname in **Settings > MCP Server** in Honeydew Studio.
  </Note>

  Run the following command to add the Honeydew MCP server:

  <Tabs>
    <Tab title="OAuth (recommended)">
      ```bash theme={null}
      gemini mcp add --transport http honeydew \
          https://mcp.honeydew.cloud/mcp
      ```

      Launch Gemini CLI with `gemini`.
      You'll be prompted to authenticate with OAuth to Honeydew.
    </Tab>

    <Tab title="API Key">
      ```bash theme={null}
      gemini mcp add --transport http honeydew \
          https://mcp.honeydew.cloud/mcp \
          --header "Authorization: Basic <YOUR_BASE64_ENCODED_API_KEY_AND_SECRET>"
      ```
    </Tab>
  </Tabs>

  #### Removing the MCP server

  To remove the Honeydew MCP server:

  ```bash theme={null}
  gemini mcp remove honeydew
  ```

  To remove the Honeydew Documentation MCP server:

  ```bash theme={null}
  gemini mcp remove honeydew-docs
  ```
</Accordion>

### VS Code and GitHub Copilot

<Accordion title="Setup instructions">
  #### Plugin Installation

  Honeydew provides a
  [plugins repository](https://github.com/honeydew-ai/honeydew-ai-coding-agents-plugins)
  with skills and tools for building semantic models
  and analyzing data through natural conversation.
  Installing the plugin sets up the Honeydew MCP servers automatically.

  **Add the Honeydew marketplace**

  1. Open your VS Code `settings.json`
     (open the Command Palette with `CMD+Shift+P` on macOS
     or `Ctrl+Shift+P` on Windows/Linux,
     then select **Preferences: Open User Settings (JSON)**)
  2. Add the Honeydew marketplace to the
     `chat.plugins.marketplaces` setting:
     ```json theme={null}
     "chat.plugins.marketplaces": [
       "honeydew-ai/honeydew-ai-coding-agents-plugins"
     ]
     ```

  **Install the plugin**

  1. Open the Extensions view
     (`CMD+Shift+X` on macOS or `Ctrl+Shift+X` on Windows/Linux)
  2. Enter `@agentPlugins` in the search field
  3. Find the **Honeydew AI** plugin and click **Install**

  The first time you install a plugin from a new marketplace,
  VS Code shows a trust prompt — review the marketplace source
  before confirming.

  **Update the plugin**

  If `extensions.autoUpdate` is enabled in VS Code settings,
  the plugin updates automatically.
  To update manually, open the Command Palette and run
  **Extensions: Check for Extension Updates**.

  #### MCP Server

  Use this section if your organization uses a custom Honeydew endpoint,
  or if you prefer to configure the MCP servers without installing the plugin.
  Disable the Honeydew MCP connection added by the plugin, then add your
  custom endpoint using the instructions below.

  Honeydew provides two MCP servers:

  * **Honeydew MCP** — connects VS Code to the Honeydew Semantic Layer
    for model exploration, data querying, and model management
  * **Honeydew Documentation MCP** — gives VS Code access to Honeydew
    documentation. No authentication required.

  <Note>
    If your organization uses a custom Honeydew hostname,
    replace `https://mcp.honeydew.cloud/mcp` with your tenant hostname.
    You can find the hostname in **Settings > MCP Server** in Honeydew Studio.
  </Note>

  1. Open the Command Palette with `CMD+Shift+P` (macOS)
     or `Ctrl+Shift+P` (Windows/Linux)
  2. Select **MCP: Add Server...**
  3. Choose **HTTP (HTTP or Server-Sent Events)**
  4. Enter the Honeydew MCP server URL:
     `https://mcp.honeydew.cloud/mcp`
  5. Enter `honeydew` as the server name

  This adds the server to your `.vscode/mcp.json` file.
  Open the file and add headers as needed:

  <Tabs>
    <Tab title="OAuth (recommended)">
      ```json theme={null}
      {
        "servers": {
          "honeydew": {
            "type": "http",
            "url": "https://mcp.honeydew.cloud/mcp"
          }
        }
      }
      ```
    </Tab>

    <Tab title="API Key">
      ```json theme={null}
      {
        "servers": {
          "honeydew": {
            "type": "http",
            "url": "https://mcp.honeydew.cloud/mcp",
            "headers": {
              "Authorization": "Basic <YOUR_BASE64_ENCODED_API_KEY_AND_SECRET>"
            }
          }
        }
      }
      ```
    </Tab>
  </Tabs>

  #### Honeydew Documentation MCP

  Give VS Code access to the Honeydew documentation through a separate MCP server.
  No authentication is required.

  Add the following to your `.vscode/mcp.json`:

  ```json theme={null}
  {
    "servers": {
      "honeydew-docs": {
        "type": "http",
        "url": "https://honeydew.ai/docs/mcp"
      }
    }
  }
  ```

  #### Removing the MCP server

  To remove the Honeydew MCP server,
  open `.vscode/mcp.json` and delete the `honeydew`
  entry from the `servers` object.
  To remove the Honeydew Documentation MCP server,
  delete the `honeydew-docs` entry from the same file.
</Accordion>

### Codex CLI

<Accordion title="Setup instructions">
  #### Plugin Installation

  Honeydew provides a
  [plugins repository](https://github.com/honeydew-ai/honeydew-ai-coding-agents-plugins)
  with skills and tools for building semantic models
  and analyzing data through natural conversation.
  Installing the plugin sets up the Honeydew MCP servers automatically.

  Add the marketplace to Codex:

  ```
  codex plugin marketplace add honeydew-ai/honeydew-ai-coding-agents-plugins
  ```

  Then launch Codex with `codex` and type `/plugins`
  to browse and install the Honeydew AI plugin.

  **Updating plugins**

  To update the Honeydew marketplace, run:

  ```
  codex plugin marketplace upgrade honeydew-ai-coding-agents-plugins
  ```

  Then launch Codex and type `/plugins` to apply updates.

  #### MCP Setup

  Use this section if your organization uses a custom Honeydew endpoint,
  or if you prefer to configure the MCP servers without installing the plugin.
  Disable the Honeydew MCP connection added by the plugin, then add your
  custom endpoint using the instructions below.

  Honeydew provides two MCP servers:

  * **Honeydew MCP** — connects Codex to the Honeydew Semantic Layer
    for model exploration, data querying, and model management
  * **Honeydew Documentation MCP** — gives Codex access to Honeydew
    documentation. No authentication required. Add it with:

    ```bash theme={null}
    codex mcp add honeydew-docs \
        --url https://honeydew.ai/docs/mcp
    ```

  <Note>
    If your organization uses a custom Honeydew hostname,
    replace `https://mcp.honeydew.cloud/mcp` with your tenant hostname.
    You can find the hostname in **Settings > MCP Server** in Honeydew Studio.
  </Note>

  **Command line**

  ```bash theme={null}
  codex mcp add honeydew \
      --url https://mcp.honeydew.cloud/mcp
  ```

  Then launch Codex with `codex`.
  You'll be prompted to authenticate
  with OAuth to Honeydew.

  After adding the server,
  open the configuration file
  at `~/.codex/config.toml` and add headers
  to the `[mcp_servers.honeydew]` section as needed.

  **TOML configuration**

  Add the following to `~/.codex/config.toml`
  (or `.codex/config.toml` in a trusted project):

  ```toml theme={null}
  [mcp_servers.honeydew]
  url = "https://mcp.honeydew.cloud/mcp"

  [mcp_servers.honeydew.env_http_headers]
  Authorization = "HONEYDEW_AUTH"
  ```

  Set the `HONEYDEW_AUTH` environment variable to
  `Basic <YOUR_BASE64_ENCODED_API_KEY_AND_SECRET>`
  (see [Authentication](#authentication)).

  #### Removing the MCP server

  To remove the Honeydew MCP server:

  ```bash theme={null}
  codex mcp remove honeydew
  ```

  To remove the Honeydew Documentation MCP server:

  ```bash theme={null}
  codex mcp remove honeydew-docs
  ```
</Accordion>

### Codex

<Accordion title="Setup instructions">
  #### Plugin Installation

  Honeydew provides a
  [plugins repository](https://github.com/honeydew-ai/honeydew-ai-coding-agents-plugins)
  with skills and tools for building semantic models
  and analyzing data through natural conversation.
  Installing the plugin sets up the Honeydew MCP servers automatically.

  Add the marketplace in Codex:

  1. Open **Plugins**
  2. Click the dropdown arrow and select **Add marketplace**
  3. Add `honeydew-ai/honeydew-ai-coding-agents-plugins`

  <Note>
    You can also add the marketplace from the
    [Codex CLI](#codex-cli):

    ```
    codex plugin marketplace add honeydew-ai/honeydew-ai-coding-agents-plugins
    ```
  </Note>

  Then install the plugin:

  1. Open **Plugins**
  2. Select the **Honeydew AI** marketplace
  3. Install the **Honeydew** plugin

  #### MCP Setup

  Use this section if your organization uses a custom Honeydew endpoint,
  or if you prefer to configure the MCP servers without installing the plugin.
  Disable the Honeydew MCP connection added by the plugin, then add your
  custom endpoint using the instructions below.

  <Note>
    If your organization uses a custom Honeydew hostname,
    replace `https://mcp.honeydew.cloud/mcp` with your tenant hostname.
    You can find the hostname in **Settings > MCP Server** in Honeydew Studio.
  </Note>

  **Honeydew MCP**

  1. Open the Codex application
  2. Go to **Settings** -> **MCP Servers**
  3. Under **Custom servers**, click **Add Server**
  4. Set the server name to `honeydew`
  5. Choose **Streamable HTTP** as the transport type
  6. Set the URL to
     `https://mcp.honeydew.cloud/mcp`
  7. Leave the **Bearer token environment variable**
     field empty
  8. Configure authentication as follows:

     **OAuth authentication**

     Codex redirects you to authenticate with Honeydew
     when connecting.
     No additional configuration is needed.

     **HTTP Basic authentication**

     Add an `Authorization` header
     to the headers list above with the value
     `Basic <YOUR_BASE64_ENCODED_API_KEY_AND_SECRET>`
     (see [Authentication](#authentication)).

  **Troubleshooting MCP authentication**

  If the Honeydew MCP server is not authenticated in Codex
  and the "Authenticate" option does not appear:

  1. Install the [Codex CLI](https://developers.openai.com/codex/cli/)
  2. Run `codex mcp login honeydew`

  **Honeydew Documentation MCP**

  Give Codex access to the Honeydew documentation
  through a separate MCP server.
  No authentication is required.

  1. Go to **Settings** -> **MCP Servers**
  2. Under **Custom servers**, click **Add Server**
  3. Set the server name to `honeydew-docs`
  4. Choose **Streamable HTTP** as the transport type
  5. Set the URL to `https://honeydew.ai/docs/mcp`

  #### Removing the MCP server

  To remove the Honeydew MCP server:

  1. Go to **Settings** -> **MCP Servers**
  2. Find `honeydew` under **Custom servers** and click **Remove**

  To remove the Honeydew Documentation MCP server:

  1. Go to **Settings** -> **MCP Servers**
  2. Find `honeydew-docs` under **Custom servers** and click **Remove**
</Accordion>

### Antigravity

<Accordion title="Setup instructions">
  #### MCP Server

  <Note>
    If your organization uses a custom Honeydew hostname,
    replace `https://mcp.honeydew.cloud/mcp` with your tenant hostname.
    You can find the hostname in **Settings > MCP Server** in Honeydew Studio.
  </Note>

  1. Open the Antigravity editor

  2. Click the **...** dropdown
     at the top of the agent panel

  3. Click **Manage MCP Servers**

  4. Click **View raw config**

  5. Add the following to `mcp_config.json`:

       <Tabs>
         <Tab title="OAuth (recommended)">
           ```json theme={null}
           {
             "name": "honeydew",
             "type": "http",
             "url": "https://mcp.honeydew.cloud/mcp"
           }
           ```
         </Tab>

         <Tab title="API Key">
           ```json theme={null}
           {
             "name": "honeydew",
             "type": "http",
             "url": "https://mcp.honeydew.cloud/mcp",
             "headers": {
               "Authorization": "Basic <YOUR_BASE64_ENCODED_API_KEY_AND_SECRET>"
             }
           }
           ```
         </Tab>
       </Tabs>

  6. Save the file

  #### Honeydew Documentation MCP

  Give Antigravity access
  to the Honeydew documentation
  through a separate MCP server.
  No authentication is required.

  1. Open the Antigravity editor
  2. Click the **...** dropdown
     at the top of the agent panel
  3. Click **Manage MCP Servers**
  4. Click **View raw config**
  5. Add the following to `mcp_config.json`:
     ```json theme={null}
     {
       "name": "honeydew-docs",
       "type": "http",
       "url": "https://honeydew.ai/docs/mcp"
     }
     ```
  6. Save the file

  #### Removing the MCP server

  To remove the Honeydew MCP server:

  1. Open the Antigravity editor
  2. Click the **...** dropdown at the top of the agent panel
  3. Click **Manage MCP Servers**
  4. Click **View raw config**
  5. Remove the `honeydew` and `honeydew-docs` entries from `mcp_config.json`
  6. Save the file
</Accordion>

### OpenCode

<Accordion title="Setup instructions">
  #### MCP Server

  <Note>
    If your organization uses a custom Honeydew hostname,
    replace `https://mcp.honeydew.cloud/mcp` with your tenant hostname.
    You can find the hostname in **Settings > MCP Server** in Honeydew Studio.
  </Note>

  <Tabs>
    <Tab title="Interactive CLI">
      Run the following command
      and follow the interactive prompts:

      ```bash theme={null}
      opencode mcp add
      ```

      When prompted, enter the following values:

      1. **Location**: Choose your preferred scope (current project or global)
      2. **MCP server name**: `honeydew`
      3. **MCP server type**: `Remote`
      4. **MCP server URL**: `https://mcp.honeydew.cloud/mcp`
      5. **OAuth authentication**: `Yes`
      6. **Preregistered client ID**: `No`
    </Tab>

    <Tab title="JSON configuration">
      Add the following to your `opencode.jsonc` file:

      <Tabs>
        <Tab title="OAuth (recommended)">
          ```json theme={null}
          {
            "$schema": "https://opencode.ai/config.json",
            "mcp": {
              "honeydew": {
                "type": "remote",
                "url": "https://mcp.honeydew.cloud/mcp",
                "oauth": {}
              }
            }
          }
          ```

          Then authenticate with Honeydew:

          ```bash theme={null}
          opencode mcp auth honeydew
          ```

          This opens a browser window to complete the OAuth authentication flow.
        </Tab>

        <Tab title="API Key">
          ```json theme={null}
          {
            "$schema": "https://opencode.ai/config.json",
            "mcp": {
              "honeydew": {
                "type": "remote",
                "url": "https://mcp.honeydew.cloud/mcp",
                "headers": {
                  "Authorization": "Basic <YOUR_BASE64_ENCODED_API_KEY_AND_SECRET>"
                }
              }
            }
          }
          ```
        </Tab>
      </Tabs>
    </Tab>
  </Tabs>

  **Re-authentication**

  To re-authenticate, check your status and log out first:

  ```bash theme={null}
  opencode mcp auth list
  opencode mcp logout honeydew
  opencode mcp auth honeydew
  ```

  #### Honeydew Documentation MCP

  Give OpenCode access to the Honeydew documentation
  through a separate MCP server.
  No authentication is required.

  <Tabs>
    <Tab title="Interactive CLI">
      Run `opencode mcp add` and enter the following values:

      1. **MCP server name**: `honeydew-docs`
      2. **MCP server type**: `Remote`
      3. **MCP server URL**: `https://honeydew.ai/docs/mcp`
      4. **OAuth authentication**: `No`
    </Tab>

    <Tab title="JSON configuration">
      Add the following to your `opencode.jsonc` file:

      ```json theme={null}
      {
        "$schema": "https://opencode.ai/config.json",
        "mcp": {
          "honeydew-docs": {
            "type": "remote",
            "url": "https://honeydew.ai/docs/mcp"
          }
        }
      }
      ```
    </Tab>
  </Tabs>

  #### Removing the MCP server

  To remove the Honeydew MCP server,
  remove the `honeydew` entry from your `opencode.jsonc` file.
  To remove the Honeydew Documentation MCP server,
  remove the `honeydew-docs` entry from the same file.
</Accordion>

### Kiro

<Accordion title="Setup instructions">
  The Kiro IDE and the Kiro CLI share the same MCP configuration files,
  so the steps below apply to both.

  #### MCP Server

  Kiro reads MCP servers from two configuration files:

  * **Workspace**: `.kiro/settings/mcp.json` (specific to the current project)
  * **User**: `~/.kiro/settings/mcp.json` (applies across all workspaces)

  If both files exist, the workspace configuration takes precedence.

  <Note>
    If your organization uses a custom Honeydew hostname,
    replace `https://mcp.honeydew.cloud/mcp` with your tenant hostname.
    You can find the hostname in **Settings > MCP Server** in Honeydew Studio.
  </Note>

  Add the Honeydew MCP server to one of these
  `mcp.json` files (workspace or user):

  <Tabs>
    <Tab title="OAuth (recommended)">
      ```json theme={null}
      {
        "mcpServers": {
          "honeydew": {
            "url": "https://mcp.honeydew.cloud/mcp"
          }
        }
      }
      ```

      When first connecting to Honeydew, Kiro provides an authentication URL.
      Open it in your browser to complete the OAuth authentication flow.
    </Tab>

    <Tab title="API Key">
      ```json theme={null}
      {
        "mcpServers": {
          "honeydew": {
            "url": "https://mcp.honeydew.cloud/mcp",
            "headers": {
              "Authorization": "Basic <YOUR_BASE64_ENCODED_API_KEY_AND_SECRET>"
            }
          }
        }
      }
      ```
    </Tab>
  </Tabs>

  In the Kiro CLI, run `/mcp` to verify the server is connected.
  In the Kiro IDE, the server appears under the MCP panel.

  #### Honeydew Documentation MCP

  Give Kiro access to the Honeydew documentation
  through a separate MCP server.
  No authentication is required.

  Add the following to your `mcp.json`:

  ```json theme={null}
  {
    "mcpServers": {
      "honeydew-docs": {
        "url": "https://honeydew.ai/docs/mcp"
      }
    }
  }
  ```

  #### Removing the MCP server

  To remove the Honeydew MCP server,
  delete the `honeydew` entry from your `mcp.json`.
  To remove the Honeydew Documentation MCP server,
  delete the `honeydew-docs` entry from the same file.
</Accordion>

### Other Clients

Any MCP-compatible client can connect
to the Honeydew MCP Server
using the standard HTTP transport.

Use the following JSON configuration
as a starting point:

<Note>
  If your organization uses a custom Honeydew hostname,
  replace `https://mcp.honeydew.cloud/mcp` with your tenant hostname.
  You can find the hostname in **Settings > MCP Server** in Honeydew Studio.
</Note>

<Tabs>
  <Tab title="OAuth (recommended)">
    ```json theme={null}
    {
      "name": "honeydew",
      "type": "http",
      "url": "https://mcp.honeydew.cloud/mcp"
    }
    ```
  </Tab>

  <Tab title="API Key">
    ```json theme={null}
    {
      "name": "honeydew",
      "type": "http",
      "url": "https://mcp.honeydew.cloud/mcp",
      "headers": {
        "Authorization": "Basic <YOUR_BASE64_ENCODED_API_KEY_AND_SECRET>"
      }
    }
    ```
  </Tab>
</Tabs>

See [Server URL](#server-url),
[Authentication](#authentication),
and [Configuration](#configuration)
for details on each parameter.

## Example Usage

Once connected, you can prompt your AI assistant with questions like:

* "What entities are available in the semantic model?"
* "Show me the attributes and metrics
  for the `orders` entity"
* "What domains are defined in the model?"
* "What tables are in the `analytics` schema?"
* "How many orders were placed last month?"
* "Create a new metric for total revenue
  on the `orders` entity"
* "What is the average order value by region
  for the last quarter?"

## Troubleshooting

### OAuth Authentication Problems

Verify your client supports OAuth, ensure you have the necessary Honeydew workspace
permissions, and attempt re-authentication through your client's MCP management interface.

**Re-authenticating in Claude Code**

Type `/mcp`, select the Honeydew MCP from the list,
choose "Clear authentication" or "Authenticate",
then follow the browser OAuth prompts to reconnect to Honeydew.

### Connection Issues

Confirm the MCP server URL matches `https://mcp.honeydew.cloud/mcp`
and verify your client's MCP configuration syntax is correct.
If your organization uses a custom hostname, check that the URL matches
your tenant hostname that appears in **Settings > MCP Server** in Honeydew Studio.

### Missing Tools

Verify authentication succeeded, check your Honeydew workspace access permissions,
and review your client's console for error messages.

### Output Exceeds Maximum Allowed Tokens (Claude)

In Claude Code, Claude Desktop, and Claude.ai, a tool call can fail with an error
that the output exceeds the maximum allowed tokens. Honeydew analysis tools such as
[`monitor_analysis`](#monitor_analysis) and
[`get_analysis_step_details`](#get_analysis_step_details) can return large results
that pass Claude's MCP output limit.

Claude warns when MCP tool output exceeds 10,000 tokens and rejects output above the
default limit of 25,000 tokens. To raise the limit, set the `MAX_MCP_OUTPUT_TOKENS`
environment variable before launching Claude:

```bash theme={null}
export MAX_MCP_OUTPUT_TOKENS=50000
claude
```

See [MCP output limits and warnings](https://code.claude.com/docs/en/mcp#mcp-output-limits-and-warnings)
in the Claude docs for details.

For additional support, contact Honeydew support at [support@honeydew.ai](mailto:support@honeydew.ai).

## Tools Available

Tools marked as *read-only* do not modify
the semantic model or the data warehouse.

<Tip>
  To expose only read-only tools, set the `ReadonlyToolsOnly: true` header
  in your MCP server configuration. When enabled, the server returns only tools
  that do not modify the semantic model or the data warehouse.
</Tip>

### Session & Workspace

#### `list_workspaces`

*read-only*

List all available workspaces.
Returns the workspace name, and the data warehouse type (`snowflake`, `databricks`, or `bigquery`).
Use the data warehouse type to inform semantic model implementation.

#### `list_workspace_branches`

*read-only*

List all branches available for a workspace.

<ParamField body="workspace_id" type="string" required>
  The name of the workspace.
</ParamField>

#### `get_session_workspace_and_branch`

*read-only*

Get the workspace and branch set for the current session.

#### `set_session_workspace_and_branch`

*read-only*

Set the workspace and branch to use for the current session.
All subsequent tool calls in the session use this workspace and branch.

<ParamField body="workspace_id" type="string" required>
  The name of the workspace.
</ParamField>

<ParamField body="branch_id" type="string" default="prod">
  The branch to use.
</ParamField>

#### `create_workspace_branch`

Create a new branch for an existing workspace.
The branch is created from the current state of the workspace's `prod` branch.
If no workspace is pinned via headers, the session switches to the new branch automatically.

<ParamField body="workspace_id" type="string" required>
  Name of the workspace to create a branch for.
</ParamField>

<ParamField body="branch_name" type="string" required>
  Name of the new branch to create.
</ParamField>

#### `delete_workspace_branch`

Delete a branch from a workspace.
This is a destructive, irreversible operation.
Always confirm the workspace name and branch name with the user before calling this tool.
The `prod` branch cannot be deleted.
If the deleted branch is the current session branch,
the session switches to `prod` automatically.

<ParamField body="workspace_id" type="string" required>
  Name of the workspace containing the branch to delete.
</ParamField>

<ParamField body="branch_name" type="string" required>
  Name of the branch to delete.
</ParamField>

#### `get_branch_history`

*read-only*

Get the change history for the current session's branch.
Returns a list of changes showing what semantic objects were modified,
by whom, and when.

<ParamField body="limit" type="number" default="50">
  Maximum number of changes to return.
</ParamField>

#### `create_pr_for_working_branch`

Create a pull request for the current session's working branch.
Returns the PR URL on success.

<ParamField body="title" type="string" required>
  Title for the pull request.
</ParamField>

<ParamField body="description" type="string">
  Description for the pull request.
</ParamField>

### Question & Analysis

#### `initiate_analysis`

*read-only*

Start or continue a data analysis. Returns a `conversation_id` —
use `monitor_analysis` to poll for progress and results,
and `abort_analysis` to stop it early.
See [Deep Analysis](/integration/context-layer/deep-analysis) for more details.

<ParamField body="question" type="string" required>
  The natural language question to ask.
</ParamField>

<ParamField body="agent" type="string">
  Agent name for a new conversation.
  Omit for follow-up questions — the agent is inherited
  from the existing conversation.
</ParamField>

<ParamField body="conversation_id" type="string">
  Existing conversation ID to continue,
  or omit to start a new conversation.
</ParamField>

#### `monitor_analysis`

*read-only*

Poll for new progress messages from an in-progress analysis.
Each call returns only messages since the last call.
Poll repeatedly until `status` is `DONE` or `NO_CHAT_CURRENTLY_RUNNING`.

<ParamField body="conversation_id" type="string" required>
  Conversation ID returned by `initiate_analysis`.
</ParamField>

<ParamField body="messages_limit" type="integer" default="10">
  Maximum number of messages to return per call.
</ParamField>

<ParamField body="from_message_id" type="integer">
  Message ID to replay from. Use `last_received_message_id`
  from a previous result to recover missed messages.
</ParamField>

#### `get_analysis_step_details`

*read-only*

Retrieve full details for a specific analysis step,
including the semantic query, SQL statement, context used,
and data retrieved in that step.

<ParamField body="conversation_id" type="string" required>
  Conversation ID returned by `initiate_analysis`.
</ParamField>

<ParamField body="step_id" type="string" required>
  Step ID from `monitor_analysis` (e.g. `STEP/0`).
</ParamField>

#### `abort_analysis`

*read-only*

Abort an in-progress analysis.
Can be resumed from the aborted point with `initiate_analysis`.

<ParamField body="conversation_id" type="string" required>
  Conversation ID returned by `initiate_analysis`.
</ParamField>

#### `list_analysis_chats`

*read-only*

Return a paginated list of analysis conversations for the current workspace,
sorted by creation time (newest first).
Admins see all conversations; non-admins see only their own.
Each entry includes the conversation ID, title, user feedback, domain, agent,
creation time, and the display name of the user who created it.

<ParamField body="limit" type="integer">
  Maximum number of conversations to return.
</ParamField>

<ParamField body="offset" type="integer">
  Number of conversations to skip for pagination.
</ParamField>

#### `provide_analysis_feedback`

Set or clear feedback on a specific analysis conversation.
There is a single feedback entry per conversation (not per question) —
it should reflect the overall quality of the entire conversation flow.

Call this after `monitor_analysis` completes and the user expresses
satisfaction or dissatisfaction with the result.
Use a short affirmative string for positive feedback (e.g. `Good`),
or the format `<Reason>: <details>` for negative feedback,
where `Reason` is one of `Chart Issue`, `Data Issue`, `Wrong Judgement`, or `Other`.

<ParamField body="conversation_id" type="string" required>
  Conversation ID of the analysis conversation.
</ParamField>

<ParamField body="feedback" type="string" required>
  Feedback text to store, or `null` to clear existing feedback.
</ParamField>

#### `get_stored_conversation`

*read-only*

Return all messages from an existing analysis conversation.
Use this to review the full content of a previous conversation.
`is_complete` in the response indicates whether the conversation
reached a terminal state.

<ParamField body="conversation_id" type="string" required>
  Conversation ID from `list_analysis_chats`.
</ParamField>

<ParamField body="with_step_ids" type="boolean" default="false">
  If `true`, include `step_start` and `step_insight` progress entries.
  If `false`, return only final responses and plan/interpretation messages.
</ParamField>

### Browse & Discovery

#### `list_entities`

*read-only*

List all entities in the semantic model with their names, descriptions, and keys.

#### `get_entity`

*read-only*

Get detailed information about an entity, including its attributes,
metrics, datasets, relations, and YAML definition.

<ParamField body="entity_name" type="string" required>
  The name of the entity.
</ParamField>

#### `get_field`

*read-only*

Get detailed information about a specific field (attribute or metric)
within an entity, including its YAML definition.

<ParamField body="entity_name" type="string" required>
  The name of the entity containing the field.
</ParamField>

<ParamField body="field_name" type="string" required>
  The name of the field.
</ParamField>

#### `list_domains`

*read-only*

List all domains in the semantic model with their names, descriptions, and entities.

#### `get_domain`

*read-only*

Get detailed information about a domain, including its entities, filters, parameters,
and YAML definition.

<ParamField body="domain_name" type="string" required>
  The name of the domain.
</ParamField>

#### `search_model`

*read-only*

Search the semantic model for entities, attributes, metrics, datasets,
dynamic datasets, domains, and global parameters matching a query string.

Use `entity.field` syntax to scope the search to fields within a specific entity.
For example, `customers.balance` finds the `balance` field on entities matching
`customers`; `customers.` returns all fields of matching entities. In `OR`/`AND`
mode, partial matches apply to both the entity and field parts — `cust.bal` matches `customers.balance`.

<ParamField body="query" type="string" required>
  The search query string.
</ParamField>

<ParamField body="search_mode" type="string" required>
  Controls how the query is matched:

  * `OR` — splits by whitespace, returns objects matching any word.
  * `AND` — splits by whitespace, returns only objects matching all words.
  * `EXACT` — uses the full string as-is, returns objects whose name or
    display name is an exact match.
</ParamField>

### Warehouse Discovery

#### `list_databases`

*read-only*

List all databases available in the connected data warehouse.

#### `list_schemas`

*read-only*

List all schemas in a specific database in the connected data warehouse.

<ParamField body="database" type="string" required>
  The database name.
</ParamField>

#### `list_tables`

*read-only*

List tables/views in a specific database and schema in the connected data warehouse.

<ParamField body="database" type="string" required>
  The database name.
</ParamField>

<ParamField body="schema" type="string" required>
  The schema name.
</ParamField>

#### `get_table_info`

*read-only*

Get detailed information about a warehouse table/view, including its columns and metadata.

<ParamField body="database" type="string" required>
  The database name.
</ParamField>

<ParamField body="schema" type="string" required>
  The schema name.
</ParamField>

<ParamField body="table" type="string" required>
  The table name.
</ParamField>

### Semantic Model

#### `import_tables`

Import tables from the connected data warehouse into the semantic model.
Each table becomes an entity with its columns as attributes.

<ParamField body="tables" type="string[]" required>
  List of fully qualified table names in the format `database.schema.table`.
</ParamField>

#### `create_entity`

Create a new entity in the semantic model
from YAML definitions.

<ParamField body="entity_yaml" type="string" required>
  The YAML definition for the entity.
</ParamField>

<ParamField body="dataset_yaml" type="string" required>
  The YAML definition for the dataset.
</ParamField>

#### `create_object`

Create a new semantic model object from a YAML definition.
Supported types: attribute, metric, dynamic dataset, domain, and global parameter.

<ParamField body="yaml_text" type="string" required>
  The YAML definition of the object.
</ParamField>

<ParamField body="force_with_error" type="boolean">
  Create the object even if validation produces errors.
</ParamField>

#### `update_object`

Update an existing semantic model object from a YAML definition.
Supported types: entity, attribute, metric, dataset, dynamic dataset, domain,
and global parameter.

<ParamField body="yaml_text" type="string" required>
  The YAML definition of the object.
</ParamField>

<ParamField body="object_key" type="string">
  The key of the object to update.
</ParamField>

<ParamField body="force_with_error" type="boolean">
  Update the object even if validation produces errors.
</ParamField>

#### `validate_object`

*read-only*

Validate a semantic model object YAML definition without creating or updating it.
Supported types: entity, attribute, metric, dataset, dynamic dataset, domain,
and global parameter.

<ParamField body="yaml_text" type="string" required>
  The YAML definition to validate.
</ParamField>

<ParamField body="object_key" type="string">
  The key of the object to validate against.
</ParamField>

#### `delete_object`

Delete a semantic model object by its key.

<ParamField body="object_key" type="string" required>
  The key of the object to delete.
</ParamField>

<ParamField body="force_with_error" type="boolean">
  Delete the object even if validation produces errors.
</ParamField>

### Agents

#### `list_agents`

*read-only*

List all agents with their names, descriptions, domains, and context references.

#### `get_agent`

*read-only*

Get detailed information about an agent, including its YAML frontmatter definition.

<ParamField body="name" type="string" required>
  Name of the agent to retrieve.
</ParamField>

#### `create_agent`

Create a new agent.

<ParamField body="agent" type="object" required>
  Metadata for the new agent.

  <Expandable title="agent fields">
    <ParamField body="name" type="string" required>
      Hierarchical name (e.g., `growth-analyst`, `finance/budget-analyst`).
    </ParamField>

    <ParamField body="display_name" type="string" required>
      Human-readable name shown in the UI.
    </ParamField>

    <ParamField body="description" type="string" required>
      Description of the agent's purpose and capabilities.
    </ParamField>

    <ParamField body="domain" type="string" required>
      The domain this agent operates in.
    </ParamField>

    <ParamField body="welcome_message" type="string">
      Introductory message shown when a user starts a session.
    </ParamField>

    <ParamField body="sample_questions" type="string[]">
      Example questions shown to users.
    </ParamField>

    <ParamField body="context" type="string[]">
      Context item names or glob patterns to load into sessions
      (e.g., `skills/**`, `knowledge/marketing/**`).
    </ParamField>

    <ParamField body="owner" type="string">
      Owner identifier for the agent.
    </ParamField>
  </Expandable>
</ParamField>

<ParamField body="markdown_text" type="string">
  Markdown body appended after the frontmatter.
  This text is injected into the prompt before every analysis session.
</ParamField>

<ParamField body="force_with_error" type="boolean" default="false">
  Create the agent even if validation produces errors.
</ParamField>

#### `update_agent`

Update an existing agent.

<ParamField body="name" type="string" required>
  Name of the agent to update.
</ParamField>

<ParamField body="agent" type="object" required>
  Full updated agent definition. All required fields from `create_agent`
  must be supplied — this is a full replacement, not a partial update.
</ParamField>

<ParamField body="markdown_text" type="string">
  Updated Markdown body for the agent.
</ParamField>

<ParamField body="force_with_error" type="boolean" default="false">
  Update the agent even if validation produces errors.
</ParamField>

#### `delete_agent`

Delete an agent by name.

<ParamField body="name" type="string" required>
  Name of the agent to delete.
</ParamField>

### Context Items

#### `list_context_items`

*read-only*

List all context items with their types, names, titles, and subtype values.

#### `get_context_item`

*read-only*

Get a context item by name.

<ParamField body="name" type="string" required>
  Name of the context item to retrieve.
</ParamField>

#### `create_context_item`

Create a new context item. Supports instruction and memory types.

<ParamField body="context_item" type="object" required>
  Metadata for the new context item.

  <Expandable title="instruction context item fields">
    <ParamField body="type" type="string" required>
      Must be `instruction`.
    </ParamField>

    <ParamField body="name" type="string" required>
      Hierarchical name
      (e.g., `knowledge/customer/churn-analysis`, `skills/reporting`).
    </ParamField>

    <ParamField body="subtype" type="string" required>
      One of `knowledge`, `skill`, or `instruction`.
    </ParamField>

    <ParamField body="title" type="string" required>
      Human-readable title for the context item.
    </ParamField>

    <ParamField body="apply" type="string" required>
      When to apply the context: `always` or `on_demand`.
    </ParamField>

    <ParamField body="description" type="string">
      Description used by the AI to decide when to load this item
      (required when `apply` is `on_demand`).
    </ParamField>

    <ParamField body="owner" type="string">
      Owner identifier.
    </ParamField>

    <ParamField body="labels" type="string[]">
      Labels for organizing context items.
    </ParamField>

    <ParamField body="related_objects" type="object[]">
      Semantic objects this context item relates to.
      Each object has a `name` (string) and `type` (`domain`, `entity`, or `field`).
    </ParamField>

    <ParamField body="external_source" type="object">
      External source to fetch content from (for `knowledge` subtype).
      Has `tool` (MCP tool name), `resource_id` (identifier in the external tool),
      and optional `cache_max_age_in_seconds` (default: `3600`).
    </ParamField>
  </Expandable>

  <Expandable title="memory context item fields">
    <ParamField body="type" type="string" required>
      Must be `memory`.
    </ParamField>

    <ParamField body="name" type="string" required>
      Hierarchical name (e.g., `events/q4-launch`, `2024/pricing-decision`).
    </ParamField>

    <ParamField body="subtype" type="string" required>
      One of `event` or `decision_trace`.
    </ParamField>

    <ParamField body="title" type="string" required>
      Human-readable title for the context item.
    </ParamField>

    <ParamField body="apply" type="string" required>
      When to apply the context: `always` or `on_demand`.
    </ParamField>

    <ParamField body="from_date" type="string" required>
      Start date of the memory period in ISO format (e.g., `2024-01-01`).
    </ParamField>

    <ParamField body="to_date" type="string">
      End date of the memory period in ISO format.
    </ParamField>

    <ParamField body="description" type="string">
      Description used by the AI to decide when to load this item
      (required when `apply` is `on_demand`).
    </ParamField>

    <ParamField body="owner" type="string">
      Owner identifier.
    </ParamField>

    <ParamField body="labels" type="string[]">
      Labels for organizing context items.
    </ParamField>

    <ParamField body="related_objects" type="object[]">
      Semantic objects this context item relates to.
      Each object has a `name` (string) and `type` (`domain`, `entity`, or `field`).
    </ParamField>

    <ParamField body="external_source" type="object">
      External source to fetch content from.
      Has `tool` (MCP tool name), `resource_id` (identifier in the external tool),
      and optional `cache_max_age_in_seconds` (default: `3600`).
    </ParamField>
  </Expandable>
</ParamField>

<ParamField body="markdown_text" type="string">
  Markdown body for the context item's content.
</ParamField>

<ParamField body="force_with_error" type="boolean" default="false">
  Create the context item even if validation produces errors.
</ParamField>

#### `update_context_item`

Update an existing context item.

<ParamField body="name" type="string" required>
  Name of the context item to update.
</ParamField>

<ParamField body="context_item" type="object" required>
  Full updated context item definition. All required fields from `create_context_item`
  must be supplied — this is a full replacement, not a partial update.
</ParamField>

<ParamField body="markdown_text" type="string">
  Updated Markdown body for the context item.
</ParamField>

<ParamField body="force_with_error" type="boolean" default="false">
  Update the context item even if validation produces errors.
</ParamField>

#### `delete_context_item`

Delete a context item by name.

<ParamField body="name" type="string" required>
  Name of the context item to delete.
</ParamField>

### Query & Preview

#### `get_sql_from_fields`

*read-only*

Generate the SQL query for a semantic layer query defined by attributes,
metrics, and filters. Returns the SQL without executing it.

<ParamField body="attributes" type="string[]">
  Fully qualified attribute names (`entity.attribute_name`).
  Supports aliases: `entity.attribute_name as alias_name`.
</ParamField>

<ParamField body="metrics" type="string[]">
  Fully qualified metric names (`entity.metric_name`) or SQL expressions
  (e.g. `SUM(entity.field)`). Supports aliases: `SUM(entity.field) as total`.
</ParamField>

<ParamField body="filters" type="string[]">
  Filter conditions (e.g. `entity.field = 'value'`,
  `entity.date_field > '2024-01-01'`).
</ParamField>

<ParamField body="order_by" type="string[]">
  List of fields to order by.
  Format: `entity.field_name` or `entity.field_name DESC`.
  Default direction is ASC.
  When using aliases, order by the alias name.
</ParamField>

<ParamField body="domain" type="string">
  The domain to query against.
</ParamField>

<ParamField body="limit" type="number" default="100">
  Maximum number of rows to return.
</ParamField>

<ParamField body="offset" type="number" default="0">
  Number of rows to skip for pagination.
</ParamField>

#### `get_data_from_fields`

*read-only*

Execute a semantic layer query defined by attributes, metrics, and filters,
and return the resulting data.

<ParamField body="attributes" type="string[]">
  Fully qualified attribute names (`entity.attribute_name`).
  Supports aliases: `entity.attribute_name as alias_name`.
</ParamField>

<ParamField body="metrics" type="string[]">
  Fully qualified metric names (`entity.metric_name`) or SQL expressions
  (e.g. `SUM(entity.field)`). Supports aliases: `SUM(entity.field) as total`.
</ParamField>

<ParamField body="filters" type="string[]">
  Filter conditions (e.g. `entity.field = 'value'`,
  `entity.date_field > '2024-01-01'`).
</ParamField>

<ParamField body="order_by" type="string[]">
  List of fields to order by.
  Format: `entity.field_name` or `entity.field_name DESC`.
  Default direction is ASC.
  When using aliases, order by the alias name.
</ParamField>

<ParamField body="domain" type="string">
  The domain to query against.
</ParamField>

<ParamField body="limit" type="integer" default="100">
  Maximum number of rows to return.
</ParamField>

<ParamField body="offset" type="integer" default="0">
  Number of rows to skip for pagination.
</ParamField>