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

# Documentation MCP server

The Anaconda documentation MCP server lets AI coding assistants search and retrieve Anaconda documentation in real time, so you get accurate, up-to-date answers without leaving your chat window or code editor.

## Connect from the contextual menu

The **Copy MCP install command** button in the contextual menu provides a one-line setup command:

![Copy MCP install command button in the contextual menu](https://mintcdn.com/anaconda-29683c67/2o4yp8zUJY9gMqyv/images/reference/copy-mcp-install-command.png?fit=max\&auto=format\&n=2o4yp8zUJY9gMqyv\&q=85\&s=f3411ed8780dd663eba582e4d02c3ccd)

This button copies the following command, which you can run in your shell application to automatically configure the MCP server in supported tools:

```bash theme={null}
npx add-mcp https://www.anaconda.com/docs/mcp
```

## Manual setup

> [tab] Claude
>
> 1. Open [Claude](https://claude.ai) or Claude Desktop.
>
> 2. In the left-hand navigation, select  **Customize**, then select  **Connectors**.
>
> 3. Click  **Add connectors**, then  **Add custom connector**.
>
>    > [!NOTE]
>    >
>    > Organization-level settings might prevent you from adding custom connectors.
>
> 4. Enter `Anaconda Docs` as the name and `https://www.anaconda.com/docs/mcp` as the remote MCP server URL.
>
> 5. Click **Add**.

> [tab] Claude Code
>
> Run the following command in your terminal:
>
> ```bash theme={null}
> claude mcp add --transport http "Anaconda Docs" https://www.anaconda.com/docs/mcp
> ```
>
> Verify the server was added:
>
> ```bash theme={null}
> claude mcp list
> ```
>
> See the [Claude Code documentation](https://code.claude.com/docs/en/mcp) for details.

> [tab] Cursor
>
> To connect the Anaconda MCP server to Cursor, click **Install in Cursor**:
>
> [Install in Cursor](cursor://anysphere.cursor-deeplink/mcp/install?name=Anaconda+Docs\&config=eyJ1cmwiOiJodHRwczovL3d3dy5hbmFjb25kYS5jb20vZG9jcy9tY3AifQ==)
>
> To manually connect the MCP server, follow these steps:
>
> 1. Use Ctrl+Shift+P (Windows)/Cmd+Shift+P (macOS) to open the command palette and search for **Open MCP settings**.
>
> 2. Under **Installed MCP Servers**, click  **New MCP Server**.
>
> 3. Paste the following in the `mcp.json` file:
>
>    ```json theme={null}
>    {
>    "mcpServers": {
>        "Anaconda Docs": {
>        "url": "https://www.anaconda.com/docs/mcp"
>        }
>    }
>    }
>    ```
>
> 4. Test the connection by asking “What tools do you have available?” in Cursor's chat. Cursor should show the Anaconda MCP server as an available tool.

> [tab] VS Code
>
> To connect the Anaconda MCP server to VS Code, click **Install in VS Code**:
>
> [Install in VS Code](https://vscode.dev/redirect/mcp/install?name=Anaconda+Docs\&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fwww.anaconda.com%2Fdocs%2Fmcp%22%7D)
>
> To manually connect the MCP server, create a `.vscode/mcp.json` file and add the following:
>
> ```json theme={null}
> {
>     "servers": {
>     "Anaconda Docs": {
>         "type": "http",
>         "url": "https://www.anaconda.com/docs/mcp"
>     }
>     }
> }
> ```
>
> To test the connection, open a new chat session (Ctrl+Alt+I on Windows/Ctrl+Cmd+I on macOS) and ask "Which MCP tools do you have available?" to confirm that the Anaconda MCP server appears in the response.
>
> See the [VS Code documentation](https://code.visualstudio.com/docs/agent-customization/mcp-servers) for details.