---
title: MCP server
description: Connect MCP clients to your per-repo server, learn what the endpoint exposes, and how to disable it.
---

When an assistant can pull raw MDX from your repository (not a one-time HTML scrape), it answers with the same wording, examples, and structure your team published. docs.page runs a [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) server for every hosted public repository.

**Before you begin**

- A published docs URL you can open in a browser (see [Agent-ready docs](/ai-agents/overview))
- A **public** GitHub repository; private repos return `404` for MCP

MCP is **on by default**. You only edit `docs.json` when you want to turn the endpoint off. For server design, tools, and access control detail, see [MCP server on Features](/features/mcp-server).

---

## Overview

Each docs.page site gets a read-only MCP endpoint scoped to that repository's owner, name, and optional ref (branch, commit, or pull request):

```text
https://docs.page/{owner}/{repo}/mcp
```

Branch and pull request previews add a `~ref` segment before `/mcp`. Custom domains serve the same path at `/mcp` on that host.

The server speaks streamable HTTP MCP. There is no write access to your GitHub repo or `docs.json`.

## How it works

### Tools agents call

| Tool | Purpose |
| --- | --- |
| `list_doc_files` | Returns `.mdx` pages in the current repository context |
| `read_doc_page` | Fetches raw MDX source for a path such as `docs/getting-started.mdx` |

`read_doc_page` returns source text (the same files under `docs/` that docs.page renders), not pre-rendered HTML. That keeps token use predictable and lets the agent cite exact headings and code blocks.

### Resources

Beyond tools, the server advertises MCP resources:

- **`docs-page-config-schema`:** JSON schema for `docs.json`
- **[Agent skills](/ai-agents/agent-skills):** when your repo includes `.agents/skills/**`, each `SKILL.md` is exposed as a markdown resource

### A typical agent session

1. Client connects to your MCP URL
2. Agent calls `list_doc_files` to see available pages
3. Agent calls `read_doc_page` for paths relevant to the user's question
4. Agent cites headings and code blocks from the returned source

Use MCP when the agent works in an editor or terminal, should load only relevant pages, or needs skill resources alongside docs. For a one-fetch catalog instead, see [llms.txt](/ai-agents/llms-txt).

## Connect from the live site

Open any page on your published docs site. MCP setup is available from two places in the UI:

| Entry point | Options |
| --- | --- |
| **Page action menu** ( **Copy page** chevron) | **Install with MCP** (opens dialog), **Connect to Cursor**, **Connect to VSCode** |
| **Command palette** (**Cmd+K** / **Ctrl+K**, empty query) | **Install MCP** (opens the same dialog) |

**Install with MCP** / **Install MCP** opens a dialog titled **Install MCP** with your endpoint URL and copy-ready snippets for Cursor, Claude Code, VS Code, and Antigravity.

**Connect to Cursor** and **Connect to VSCode** skip the dialog and register the server via a one-click deep link (`cursor://…` or `vscode:mcp/install?…`) using the MCP URL for the site you have open.

The command palette shows **Install MCP** only when MCP is enabled (`mcp.enabled` is not `false`). The page menu lists MCP items on every hosted page.

## Connect manually

When you cannot use the live site UI, configure a client by hand:

<Tabs>
  <TabItem label="Cursor" value="cursor">

Create or edit `.cursor/mcp.json`:

```json
{
  "mcpServers": {
    "owner-repo": {
      "url": "https://docs.page/owner/repo/mcp"
    }
  }
}
```

Replace `owner`, `repo`, and the URL with your repository values (or copy from **Install MCP** on the live site).

  </TabItem>
  <TabItem label="Claude Code" value="claude">

```bash
claude mcp add --transport http \
  https://docs.page/owner/repo/mcp
```

  </TabItem>
</Tabs>

After connecting, invoke `list_doc_files`, then `read_doc_page` with a path from the listing.

## Disable MCP (optional)

To keep a public site but block programmatic source access, set `mcp.enabled` to `false` in `docs.json`:

```json
{
  "mcp": {
    "enabled": false
  }
}
```

Commit and publish. The MCP route returns `404`, **Install MCP** disappears from the command palette, and MCP deep links point at an unavailable endpoint. [llms.txt](/ai-agents/llms-txt) exports are unaffected.

## Related

- [Agent-ready docs](/ai-agents/overview): how MCP fits alongside llms.txt and Ask AI
- [Page actions](/features/public-github-hosting#page-actions): **Install with MCP**, **Connect to Cursor**, and **Connect to VSCode** in the header menu
- [MCP server on Features](/features/mcp-server): server descriptor, access control, and URL patterns
- [Agent skills](/ai-agents/agent-skills): expose `.agents/skills` as MCP resources
- [HTTP endpoints](/reference/http-endpoints): MCP route lookup