# LLMS.txt Documentation

> Use this tool when you need to access documentation sources seamlessly during coding sessions, as it solves the problem of manually searching for documentation by fetching and parsing llms.txt files from specified URLs. It takes in configuration inputs via YAML, JSON, or direct URL specification and outputs parsed documentation, allowing for customizable timeouts and HTTP redirect following. Use MCPDoc in contexts where integration with AI assistants like Claude Code is required for efficient documentation lookup.

Canonical page: https://skillsregistry.net/skills/langchain-mcpdoc  
JSON: https://api.skillsregistry.net/v1/skills/langchain-mcpdoc

## Description

MCPDoc is a server that provides documentation access from llms.txt files through the Model Control Protocol. It allows AI assistants to query documentation sources like LangGraph by fetching and parsing llms.txt files from specified URLs. The implementation supports multiple configuration methods including YAML, JSON, or direct URL specification, and offers features like HTTP redirect following and customizable timeouts. Built for integration with Claude Code and other MCP-compatible assistants, MCPDoc enables seamless documentation lookup during coding sessions without requiring users to leave their conversation interface.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-04-29

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/langchain-mcpdoc)
- **Repository:** <https://github.com/langchain-ai/mcpdoc>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "langchain-mcpdoc"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/langchain-mcpdoc` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/langchain-mcpdoc/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt