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

# AI access via MCP and llms.txt

> Connect Extension.js documentation to your AI tools via the hosted MCP server, or pull structured summaries from the llms.txt endpoint.

Access Extension.js documentation through two standard AI-accessible surfaces. This lets your editor and assistants answer questions from current documentation rather than outdated training data.

<Note>
  This page is about giving assistants the **docs** — answering "how do I…" from
  current content. To let an assistant **drive the tooling** (run a dev session,
  stream logs, inspect the DOM, trigger an action, reload), see the separate
  control server in [Chrome DevTools MCP with
  Extension.js](/docs/integrations/chrome-devtools-mcp).
</Note>

## Hosted MCP (Model Context Protocol) server

The docs site exposes a [Model Context Protocol](https://modelcontextprotocol.io) server at:

```
https://extensionjs.mintlify.app/mcp
```

Point any MCP-compatible client at this URL and it gains tools to search the docs, fetch specific pages, and answer questions from current content.

### One-click install

Each page has a contextual menu (top-right of the page) with install buttons for common clients: **Claude**, **Cursor**, **VS Code**, and **ChatGPT**. Use those for the shortest path.

### Manual install

<CodeGroup>
  ```json Claude Desktop (claude_desktop_config.json) theme={null}
  {
    "mcpServers": {
      "extensionjs": {
        "url": "https://extensionjs.mintlify.app/mcp"
      }
    }
  }
  ```

  ```json Cursor (.cursor/mcp.json) theme={null}
  {
    "mcpServers": {
      "extensionjs": {
        "url": "https://extensionjs.mintlify.app/mcp"
      }
    }
  }
  ```

  ```jsonc VS Code (settings.json) theme={null}
  "mcp.servers": {
    "extensionjs": {
      "url": "https://extensionjs.mintlify.app/mcp"
    }
  }
  ```

  ```bash Claude Code theme={null}
  claude mcp add --transport http extensionjs https://extensionjs.mintlify.app/mcp
  ```
</CodeGroup>

After installing, ask your assistant something like *"How do I configure browser-specific manifest fields in Extension.js?"* The assistant consults the MCP tools and cites docs pages.

## llms.txt

The documentation provides a static, machine-friendly index at:

* [`/llms.txt`](https://extensionjs.mintlify.app/llms.txt): short index of all pages
* [`/llms-full.txt`](https://extensionjs.mintlify.app/llms-full.txt): full-content bundle for ingestion

Use these when you want to feed the docs directly into a retrieval pipeline or summarize them in a custom agent. Extension.js regenerates them on every docs deploy.

## Per-page AI actions

The page-level contextual menu also offers:

* **Copy page:** copies the current page as Markdown for pasting into chats
* **View as Markdown:** opens the raw Markdown source in a new tab
* **Ask ChatGPT / Claude / Perplexity:** opens the respective assistant pre-loaded with the page as context

## Best practices

* Prefer the MCP server when you want the assistant to reason across multiple pages and keep answers current.
* Prefer `llms-full.txt` for offline tooling, evaluations, or custom RAG (retrieval-augmented generation) pipelines.
* Use the per-page actions for quick spot questions about the page you are already reading.