> For the complete documentation index, see [llms.txt](https://roam-tui.avelino.run/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://roam-tui.avelino.run/mcp-server/mcp.md).

# Overview

The roam-sdk includes a built-in [Model Context Protocol](https://modelcontextprotocol.io/) (MCP) server that exposes your Roam graph to AI assistants like Claude, Cursor, and other MCP-compatible clients.

## Features

* **18 tools** covering read, write, search, and export operations
* Runs over **stdio transport** — works with any MCP client
* **Batch writes** — execute multiple operations in a single API call
* **Full-text search** — search inside block content, not just page titles
* **Daily note access** — retrieve notes by date or today's note
* **Markdown export** — convert pages to clean markdown
* **Graph statistics** — page and block counts at a glance

## Quick start

```bash
# Run directly
roam --mcp

# Or via npx (no install needed)
npx roam-tui@latest --mcp
```

The server reads config from `~/.config/roam-tui/config.toml` or environment variables.

## Next steps

* [Setup & Configuration](/mcp-server/setup.md) — configure your MCP client
* [Tools Reference](/mcp-server/tools.md) — all 18 tools with parameters and examples


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://roam-tui.avelino.run/mcp-server/mcp.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.