miamcpdoc 0.0.43

Mia's Server llms-txt documentation over MCP

MCP LLMS-TXT Documentation Server (miamcpdoc)

𝕄𝕚𝕖𝕥𝕥𝕖❜𝕊𝕡𝕣𝕚𝕥𝕖 🌸

Overview

llms.txt 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 offers a way for developers to have full control over tools used by these applications. Here, we create an open source MCP server 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.

llms-txt

You can find llms.txt files for langgraph and langchain here:

Library	llms.txt
LangGraph Python	https://langchain-ai.github.io/langgraph/llms.txt
LangGraph JS	https://langchain-ai.github.io/langgraphjs/llms.txt
LangChain Python	https://python.langchain.com/llms.txt
LangChain JS	https://js.langchain.com/llms.txt

Quickstart

Quick Setup

1. Initialize Configuration

Create a config.yaml file in your current directory:

# Install and create basic config.yaml
uvx --from miamcpdoc miamcpdoc --init

# Create config.yaml with interactive prompts
uvx --from miamcpdoc miamcpdoc --init --interactive

# Use default bundled configuration (includes LangGraph, JGTPY, Coaiapy)
uvx --from miamcpdoc miamcpdoc --default

2. Run the MCP Server

# Use your config.yaml
uvx --from miamcpdoc miamcpdoc --yaml config.yaml

# Use default bundled configuration
uvx --from miamcpdoc miamcpdoc --default

# Serve via HTTP/SSE (web-accessible)  
uvx --from miamcpdoc miamcpdoc --yaml config.yaml --transport sse --host 0.0.0.0 --port 8000

Configuration Examples

Basic config.yaml (created by --init)

- name: LangGraph Python
  llms_txt: https://langchain-ai.github.io/langgraph/llms.txt
  description: LangGraph documentation for building stateful, multi-actor applications

- name: JGTPY Trading Framework
  llms_txt: https://jgtpy.jgwill.com/llms.txt
  description: JGT Python trading framework for market data and technical analysis

- name: Coaiapy AI Platform
  llms_txt: https://coaiapy.jgwill.com/llms.txt
  description: Coaiapy AI platform documentation and integration guides

Install uv (if needed)

• Please see official uv docs for other ways to install uv.

curl -LsSf https://astral.sh/uv/install.sh | sh

Note: Security and Domain Access Control

For security reasons, miamcpdoc implements strict domain access controls:

1. Remote llms.txt files: When you specify a remote llms.txt URL (e.g., https://langchain-ai.github.io/langgraph/llms.txt), miamcpdoc automatically adds only that specific domain (langchain-ai.github.io) to the allowed domains list. This means the tool can only fetch documentation from URLs on that domain.

2. Local llms.txt files: When using a local file, NO domains are automatically added to the allowed list. You MUST explicitly specify which domains to allow using the --allowed-domains parameter.

3. Adding additional domains: To allow fetching from domains beyond those automatically included:

   • Use --allowed-domains domain1.com domain2.com to add specific domains
   • Use --allowed-domains '*' to allow all domains (use with caution)

This security measure prevents unauthorized access to domains not explicitly approved by the user, ensuring that documentation can only be retrieved from trusted sources.

(Optional) Test the MCP server locally:

# Test with default configuration
uvx --from miamcpdoc miamcpdoc --default --transport sse --port 8082 --host localhost

# Test with custom URLs
uvx --from miamcpdoc miamcpdoc \
    --urls "LangGraph:https://langchain-ai.github.io/langgraph/llms.txt" "LangChain:https://python.langchain.com/llms.txt" \
    --transport sse \
    --port 8082 \
    --host localhost

Or use the specialized server commands:

# AI SDK documentation
uvx --from miamcpdoc miamcpdoc-aisdk

# Hugging Face documentation  
uvx --from miamcpdoc miamcpdoc-huggingface

# LangGraph documentation
uvx --from miamcpdoc miamcpdoc-langgraph

# What is LLMs documentation
uvx --from miamcpdoc miamcpdoc-llms

# Creative Frameworks documentation (RISE, Narrative Remixing, Creative Orientation)
uvx --from miamcpdoc miamcpdoc-creative

• This should run at: http://localhost:8082

• Run MCP inspector and connect to the running server:

npx @modelcontextprotocol/inspector

• 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. Choose one of these configurations:

Option 1: Use default bundled configuration (recommended)

{
  "mcpServers": {
    "miamcpdoc-default": {
      "command": "uvx",
      "args": [
        "--from",
        "miamcpdoc", 
        "miamcpdoc",
        "--default"
      ]
    }
  }
}

Option 2: Use custom config.yaml

{
  "mcpServers": {
    "miamcpdoc-custom": {
      "command": "uvx",
      "args": [
        "--from",
        "miamcpdoc",
        "miamcpdoc", 
        "--yaml",
        "config.yaml"
      ]
    }
  }
}

Option 3: Direct URL specification

{
  "mcpServers": {
    "langgraph-docs-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "miamcpdoc",
        "miamcpdoc",
        "--urls",
        "LangGraph:https://langchain-ai.github.io/langgraph/llms.txt",
        "LangChain:https://python.langchain.com/llms.txt"
      ]
    }
  }
}

• Confirm that the server is running in your Cursor Settings/MCP tab.
• Best practice is to then update Cursor Global (User) rules.
• Open Cursor Settings/Rules and update User Rules with the following (or similar):

for ANY question about LangGraph, use the langgraph-docs-mcp server to help answer -- 
+ call list_doc_sources tool to get the available llms.txt file
+ call fetch_docs tool to read it
+ reflect on the urls in llms.txt 
+ reflect on the input question 
+ call fetch_docs on any urls relevant to the question
+ use this to answer the question

• CMD+L (on Mac) to open chat.
• Ensure agent is selected.

Then, try an example prompt, such as:

what are types of memory in LangGraph?

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.

• Update Windsurf Rules/Global rules with the following (or similar):

for ANY question about LangGraph, use the langgraph-docs-mcp server to help answer -- 
+ call list_doc_sources tool to get the available llms.txt file
+ call fetch_docs tool to read it
+ reflect on the urls in llms.txt 
+ reflect on the input question 
+ call fetch_docs on any urls relevant to the question

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.

[!Note] If you run into issues with Python version incompatibility when trying to add MCPDoc tools to Claude Desktop, you can explicitly specify the filepath to python executable in the uvx command.

Example configuration

{
  "mcpServers": {
    "langgraph-docs-mcp": {
      "command": "uvx",
      "args": [
        "--python",
        "/path/to/python",
        "--from",
        "miamcpdoc",
        "miamcpdoc",
        "--urls",
        "LangGraph:https://langchain-ai.github.io/langgraph/llms.txt",
        "--transport",
        "stdio"
      ]
    }
  }
}

[!Note] Currently (3/21/25) it appears that Claude Desktop does not support rules for global rules, so appending the following to your prompt.

<rules>
for ANY question about LangGraph, use the langgraph-docs-mcp server to help answer -- 
+ call list_doc_sources tool to get the available llms.txt file
+ call fetch_docs tool to read it
+ reflect on the urls in llms.txt 
+ reflect on the input question 
+ call fetch_docs on any urls relevant to the question
</rules>

• 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, run this command to add the MCP server to your project:

claude mcp add-json langgraph-docs '{"type":"stdio","command":"uvx" ,"args":["--from", "miamcpdoc", "miamcpdoc", "--urls", "langgraph:https://langchain-ai.github.io/langgraph/llms.txt", "--urls", "LangChain:https://python.langchain.com/llms.txt"]}' -s local

• You will see ~/.claude.json updated.
• Test by launching Claude Code and running to view your tools:

$ Claude
$ /mcp 

[!Note] Currently (3/21/25) it appears that Claude Code does not support rules for global rules, so appending the following to your prompt.

<rules>
for ANY question about LangGraph, use the langgraph-docs-mcp server to help answer -- 
+ call list_doc_sources tool to get the available llms.txt file
+ call fetch_docs tool to read it
+ reflect on the urls in llms.txt 
+ reflect on the input question 
+ call fetch_docs on any urls relevant to the question
</rules>

Then, try the example prompt:

• It will ask to approve tool calls.

Available CLI Commands

Main Command

• miamcpdoc - General-purpose MCP server for custom llms.txt files

Specialized Documentation Servers

• miamcpdoc-aisdk - Vercel AI SDK documentation (ai-sdk.dev)
• miamcpdoc-huggingface - Hugging Face ecosystem documentation (Transformers, Diffusers, Accelerate, Hub, Python Hub)
• miamcpdoc-langgraph - LangGraph and LangChain Python documentation
• miamcpdoc-llms - What is LLMs documentation (llmstxt.org)
• miamcpdoc-creative - Creative Frameworks documentation (RISE, Narrative Remixing, Creative Orientation)

Creative Frameworks Server (miamcpdoc-creative)

The miamcpdoc-creative command provides access to comprehensive creative development frameworks including:

• Creative Orientation Framework - Proactive manifestation vs reactive elimination approaches
• Narrative Remixing Framework - Story transformation across domains while preserving emotional architecture
• RISE Framework - Creative-oriented reverse engineering methodology
• Non-Creative Orientation Conversion - Approaches for transforming reactive patterns

Usage

# Run the creative frameworks MCP server
miamcpdoc-creative

# Or use with uvx
uvx --from miamcpdoc miamcpdoc-creative

Available Documentation Sources

When connected to an MCP client, the server provides access to:

• CreativeOrientation - Core creative vs reactive principles
• NarrativeRemixing - Contextual transposition and story transformation
• RISEFramework - Reverse engineering for creative archaeology
• NonCreativeOrientationApproach - Converting reactive approaches to creative ones

Example MCP Configuration

{
  "mcpServers": {
    "creative-frameworks": {
      "command": "uvx",
      "args": [
        "--from",
        "miamcpdoc", 
        "miamcpdoc-creative"
      ]
    }
  }
}

Other Specialized Servers

AI SDK Server (miamcpdoc-aisdk)

Provides access to Vercel AI SDK documentation for building AI-powered applications.

Usage:

miamcpdoc-aisdk

MCP Configuration:

{
  "mcpServers": {
    "ai-sdk-docs": {
      "command": "uvx",
      "args": ["--from", "miamcpdoc", "miamcpdoc-aisdk"]
    }
  }
}

Hugging Face Server (miamcpdoc-huggingface)

Comprehensive access to Hugging Face ecosystem documentation including Transformers, Diffusers, Accelerate, Hub, and Python Hub.

Usage:

miamcpdoc-huggingface

MCP Configuration:

{
  "mcpServers": {
    "huggingface-docs": {
      "command": "uvx",
      "args": ["--from", "miamcpdoc", "miamcpdoc-huggingface"]
    }
  }
}

LangGraph Server (miamcpdoc-langgraph)

Access to both LangGraph and LangChain Python documentation for building agentic applications.

Usage:

miamcpdoc-langgraph

MCP Configuration:

{
  "mcpServers": {
    "langgraph-docs": {
      "command": "uvx",
      "args": ["--from", "miamcpdoc", "miamcpdoc-langgraph"]
    }
  }
}

LLMs Information Server (miamcpdoc-llms)

Provides access to foundational information about LLMs and the llms.txt standard.

Usage:

miamcpdoc-llms

MCP Configuration:

{
  "mcpServers": {
    "llms-info": {
      "command": "uvx",
      "args": ["--from", "miamcpdoc", "miamcpdoc-llms"]
    }
  }
}

Command-line Interface

The miamcpdoc command provides a simple CLI for launching the documentation server.

You can specify documentation sources in three ways, and these can be combined:

1. Using a YAML config file:

• This will load the LangGraph Python documentation from the sample_config.yaml file in this repo.

miamcpdoc --yaml sample_config.yaml

2. Using a JSON config file:

• This will load the LangGraph Python documentation from the sample_config.json file in this repo.

miamcpdoc --json sample_config.json

3. 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.
• You can specify multiple URLs by using the --urls parameter multiple times.
• This is how we loaded llms.txt for the MCP server above.

miamcpdoc --urls LangGraph:https://langchain-ai.github.io/langgraph/llms.txt --urls LangChain:https://python.langchain.com/llms.txt

You can also combine these methods to merge documentation sources:

miamcpdoc --yaml sample_config.yaml --json sample_config.json --urls LangGraph:https://langchain-ai.github.io/langgraph/llms.txt --urls LangChain:https://python.langchain.com/llms.txt

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:

miamcpdoc --yaml sample_config.yaml --follow-redirects --timeout 15

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:

YAML Configuration Example (sample_config.yaml)

# Sample configuration for miamcpdoc server
# Each entry must have a llms_txt URL and optionally a name
- name: LangGraph Python
  llms_txt: https://langchain-ai.github.io/langgraph/llms.txt

JSON Configuration Example (sample_config.json)

[
  {
    "name": "LangGraph Python",
    "llms_txt": "https://langchain-ai.github.io/langgraph/llms.txt"
  }
]

Programmatic Usage

from miamcpdoc.main import create_server

# Create a server with documentation sources
server = create_server(
    [
        {
            "name": "LangGraph Python",
            "llms_txt": "https://langchain-ai.github.io/langgraph/llms.txt",
        },
        # You can add multiple documentation sources
        # {
        #     "name": "Another Documentation",
        #     "llms_txt": "https://example.com/llms.txt",
        # },
    ],
    follow_redirects=True,
    timeout=15.0,
)

# Run the server
server.run(transport="stdio")