MCP LLMS-TXT Documentation Server
Overview
[llms.txt](https://llmstxt.org/) is a website index for LLMs, providing background information, guidance, and links to detailed markdown files. IDEs like Cursor and Windsurf or apps like Claude Code/Desktop can use `llms.txt` to retrieve context for tasks. However, these apps use different built-in tools to read and process files like `llms.txt`. The retrieval process can be opaque, and there is not always a way to audit the tool calls or the context returned.
[MCP](https://github.com/modelcontextprotocol) offers a way for developers to have *full control* over tools used by these applications. Here, we create [an open source MCP server](https://github.com/modelcontextprotocol) to provide MCP host applications (e.g., Cursor, Windsurf, Claude Code/Desktop) with (1) a user-defined list of `llms.txt` files and (2) a simple `fetch_docs` tool read URLs within any of the provided `llms.txt` files. This allows the user to audit each tool call as well as the context returned.
Quickstart
Install uv
- Please see [official uv docs](https://docs.astral.sh/uv/getting-started/installation/#installation-methods) for other ways to install `uv`.
Choose an `llms.txt` file to use.
- For example, [here's](https://langchain-ai.github.io/langgraph/llms.txt) the LangGraph `llms.txt` file.
(Optional) Test the MCP server locally with your `llms.txt` file of choice:
- This should run at: http://localhost:8082
- Run [MCP inspector](https://modelcontextprotocol.io/docs/tools/inspector) and connect to the running server:
- Here, you can test the `tool` calls.
Connect to Cursor
- Open `Cursor Settings` and `MCP` tab.
- This will open the `~/.cursor/mcp.json` file.
- Paste the following into the file (we use the `langgraph-docs-mcp` name and link to the LangGraph `llms.txt`).
- Confirm that the server is running in your `Cursor Settings/MCP` tab.
- `CMD+L` (on Mac) to open chat.
- Ensure `agent` is selected.
Then, try an example prompt, such as:
Connect to Windsurf
- Open Cascade with `CMD+L` (on Mac).
- Click `Configure MCP` to open the config file, `~/.codeium/windsurf/mcp_config.json`.
- Update with `langgraph-docs-mcp` as noted above.
- `CMD+L` (on Mac) to open Cascade and refresh MCP servers.
- Available MCP servers will be listed, showing `langgraph-docs-mcp` as connected.
Then, try the example prompt:
- It will perform your tool calls.
Connect to Claude Desktop
- Open `Settings/Developer` to update `~/Library/Application\ Support/Claude/claude_desktop_config.json`.
- Update with `langgraph-docs-mcp` as noted above.
- Restart Claude Desktop app.
- You will see your tools visible in the bottom right of your chat input.
Then, try the example prompt:
- It will ask to approve tool calls as it processes your request.
Connect to Claude Code
- In a terminal after installing [Claude Code](https://docs.anthropic.com/en/docs/agents-and-tools/claude-code/overview), run this command to add the MCP server to your project:
- You will see `~/.claude.json` updated.
- Test by launching Claude Code and running to view your tools:
Then, try the example prompt:
- It will ask to approve tool calls.
Command-line Interface
The `mcpdoc` command provides a simple CLI for launching the documentation server.
You can specify documentation sources in three ways, and these can be combined:
- Using a YAML config file:
- This will load the LangGraph Python documentation from the `sample_config.yaml` file in this repo.
- Using a JSON config file:
- This will load the LangGraph Python documentation from the `sample_config.json` file in this repo.
- Directly specifying llms.txt URLs with optional names:
- URLs can be specified either as plain URLs or with optional names using the format `name:url`.
- This is how we loaded `llms.txt` for the MCP server above.
You can also combine these methods to merge documentation sources:
Additional Options
- `--follow-redirects`: Follow HTTP redirects (defaults to False)
- `--timeout SECONDS`: HTTP request timeout in seconds (defaults to 10.0)
Example with additional options:
This will load the LangGraph Python documentation with a 15-second timeout and follow any HTTP redirects if necessary.
Configuration Format
Both YAML and JSON configuration files should contain a list of documentation sources.
Each source must include an `llms_txt` URL and can optionally include a `name`: