mcpField
L
langchain-mcp

langchain-mcp

Local
github.com/baixiangerDeveloper Tools4Updated 15w ago
Repository

About langchain-mcp

langchain-mcp provides documentation and code search for LangChain, LangGraph, LangSmith, and DeepAgents developers, alongside LangGraph agent debugging. It connects to a local development server to inspect threads, runs, state, and traces, and offers failure analysis and prompt suggestions.

Key features

  1. 01Search documentation, tutorials, and source code
  2. 02List LangGraph threads and runs
  3. 03Inspect agent state, checkpoints, and traces
  4. 04Analyze why a run failed
  5. 05Get suggestions for improving prompts

Use cases

  1. 01Find implementation references for LangChain or DeepAgents
  2. 02Review local LangGraph threads and runs
  3. 03Investigate failed runs and agent issues
  4. 04Refine agent prompts based on debugging

MCP support

Provides documentation and code search and LangGraph debugging tools to MCP clients. Debugging tools connect to a local langgraph dev server, at localhost:2024 by default.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "baixianger-langchain": {
      "command": "npx",
      "args": [
        "-y",
        "langchain-mcp"
      ]
    }
  }
}
Run commandnpx -y langchain-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmlangchain-mcp2.0.0

Tools

10

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
limitintegerNoMax results (1-20)
querystringYesSearch query

Details

From the project README

langchain-mcp

Give Claude superpowers for LangChain development

npm version License: MIT

Website · GitHub · Sponsor

Features

Knowledge Search

Search LangChain, LangGraph, LangSmith & DeepAgents documentation and source code instantly from Claude.

LangGraph Agent Debugging (New in v2!)

Debug your LangGraph agents like Polly - connect to your local langgraph dev server and:

  • List threads, runs, and traces
  • Inspect agent state and checkpoints
  • Ask "Why did this fail?" and get AI-powered analysis
  • Get suggestions to improve your agent's prompts

Install

npm i -g langchain-mcp
langchain-mcp login
claude mcp add langchain-mcp -- langchain-mcp
Claude Desktop config

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "langchain-mcp": {
      "command": "langchain-mcp"
    }
  }
}

Tools

Search (requires login)
ToolDescription
search_docsSearch documentation and tutorials
search_langchain_codeSearch LangChain source code
search_langgraph_codeSearch LangGraph source code
search_deepagents_codeSearch DeepAgents source code
Debug LangGraph Agents (free, no login)
ToolDescription
langgraph_list_threadsList threads from local server
langgraph_get_threadGet thread details
langgraph_get_thread_stateGet state/checkpoint
langgraph_list_runsList runs for a thread
langgraph_get_runGet run trace details

Debug Your Agents

# Start your LangGraph server
langgraph dev

Then ask Claude:

  • "List my LangGraph threads"
  • "What went wrong with thread abc123?"
  • "Summarize the last run"
  • "How can I improve this agent?"

Connects to localhost:2024 by default.

Pricing

FeatureCost
Doc/Code Search$5 free credits (~2000 searches)
LangGraph DebuggingFree forever

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.