# Using Haystack Enterprise Documentation with AI

# Using <ProductName /> Documentation with AI

Connect your AI assistant to search and retrieve information from <ProductShortName /> documentation using the MCP server. You can also copy and export single pages in Markdown format to use them in your AI assistant.

***

## Use the <ProductShortName /> Documentation MCP Server

The <ProductShortName /> documentation is available as a Model Context Protocol (MCP) server that you can connect to your AI assistant to search this documentation directly. 

The MCP server is free to use and requires no authentication.

### Server URL

The documentation MCP server is available at: 

```
https://docs.cloud.deepset.ai/api/mcp
```

### Server Tools 

The MCP server comes with two tools:
- `search_docs`: Search the <ProductShortName /> documentation.
- `list_doc_sections`: List all main documentation sections.

### Connect to Cursor

Add this code to your Cursor MCP settings (.cursor/mcp.json) in your project or global settings:

```json
{
  "mcpServers": {
    "deepset-docs": {
      "url": "https://docs.cloud.deepset.ai/api/mcp"
    }
  }
}
```

### Connect to Claude Desktop

Add this code to your Claude Desktop configuration (*~/Library/Application Support/Claude/claude_desktop_config.json* on macOS or %APPDATA%\Claude\ on Windows):

```json
{
  "mcpServers": {
    "deepset-docs": {
      "url": "https://docs.cloud.deepset.ai/api/mcp"
    }
  }
}
```

### Connect to VS Code

Add this code to your VS Code settings (.vscode/mcp.json):

```json
{
  "mcpServers": {
    "deepset-docs": {
      "url": "https://docs.cloud.deepset.ai/api/mcp"
    }
  }
}
```

## Copy Single Pages

You can also copy a page as Markdown that LLMs can easily read. Use the **Copy** button in the top right corner of a page.

<ClickableImage src="/img/getting-started/copy_dropdown.png" alt="Copy button in the top right corner of a page" size="large" />

Expand the button to view additional options.