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

# Docs MCP Server

> Use AI tools to build Evidence reports with the Evidence Docs MCP server.

## What is MCP?

The Model Context Protocol is an open standard that enables AI applications to connect to external data sources and tools. The Evidence Docs MCP server allows AI assistants to search and read the Evidence documentation.

The server is available at [https://evidence.studio/mcp](https://evidence.studio/mcp) and uses Streamable HTTP.

## Built-in to Evidence Editor

The Docs MCP server is **integrated into the Evidence Editor AI chat by default**. When you use the AI assistant in the Evidence Editor, it automatically has access to all Evidence documentation and component information—no additional configuration needed.

## Adding to Other AI Tools

You can add the Evidence Docs MCP server to other AI tools that support MCP:

<Tabs>
  <Tab title="Claude Code">
    ```bash theme={null}
    claude mcp add --transport http evidence-studio https://evidence.studio/mcp
    ```
  </Tab>

  <Tab title="Cursor">
    Add the following to your Cursor MCP configuration (`.cursor/mcp.json`):

    ```json theme={null}
    {
      "mcpServers": {
        "evidence-studio": {
          "url": "https://evidence.studio/mcp"
        }
      }
    }
    ```
  </Tab>

  <Tab title="ChatGPT">
    ChatGPT requires enabling Developer Mode to use MCP servers:

    1. Go to [ChatGPT Apps](https://chatgpt.com/apps)
    2. Open the **Settings** menu (gear icon)
    3. Go to **Advanced** and toggle **Developer Mode** on
    4. Click **Create App**
    5. Add an image (e.g., the [Evidence logo](https://github.com/evidence-dev/media-kit/blob/main/png/logo-square-white-on-black.png))
    6. Set the name to "Evidence"
    7. Paste the URL: `https://evidence.studio/mcp`
    8. Set Auth to **No Auth**
    9. Save the app

    The Evidence documentation tools will now be available in your ChatGPT conversations.
  </Tab>

  <Tab title="Claude.ai">
    1. Go to [Claude.ai Settings → Connectors](https://claude.ai/settings/connectors)
    2. Click **Add Custom Connector**
    3. Enter a name (e.g., "Evidence Docs")
    4. Paste the Remote MCP server URL: `https://evidence.studio/mcp`
    5. Click **Add** to save

    The Evidence documentation tools will now be available in your Claude.ai conversations.
  </Tab>
</Tabs>

## Available Tools

The Docs MCP server provides the following tools for AI assistants:

| Tool                       | Description                                                                                         |
| -------------------------- | --------------------------------------------------------------------------------------------------- |
| `list_components`          | Get the full list of Evidence components organized by category                                      |
| `get_component`            | Get metadata for a component including name, description, category, example, and attributes summary |
| `get_component_attributes` | Get detailed attribute information for a component (type, required, default, description)           |
| `get_component_examples`   | Get all code examples for a specific component                                                      |
| `list_docs`                | List all documentation pages with titles and paths, optionally filtered by category                 |
| `read_doc`                 | Get the full content of a documentation page                                                        |
| `search_docs`              | Search across all Evidence documentation                                                            |

## LLM-Friendly Documentation

For AI tools that don't support MCP, the Evidence documentation is also available in plain text formats:

* [docs.evidence.studio/llms.txt](https://docs.evidence.studio/llms.txt) - Sitemap of all documentation pages
* [docs.evidence.studio/llms-full.txt](https://docs.evidence.studio/llms-full.txt) - Full documentation in a single markdown file