Langchain MCP Server

Semantic search for LangChain, LangGraph, LangSmith & DeepAgents docs and source code.

Local serverstdioPython

What is the Langchain MCP server?

Semantic search for LangChain, LangGraph, LangSmith & DeepAgents docs and source code. Exposed over MCP by the langchain mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.

What it actually does

Add the following configuration to your client's config file:

  • Semantic Search — - Natural language queries across all LangChain ecosystem docs
  • Source Code Search — - Find code examples in Python and JavaScript repositories
  • MCP Protocol — - Works seamlessly with Claude Code, Claude Desktop, Cursor, and any MCP-compatible client
  • Production Ready — - Scalable API with authentication and usage tracking
  • Fast & Accurate — - Powered by ChromaDB and OpenRouter embeddings

Its toolset

Everything the assistant can do here goes through one of these:

  • search_docs — Search documentation, references, and tutorials
  • search_langchain_code — Search LangChain source code
  • search_langgraph_code — Search LangGraph source code
  • search_deepagents_code — Search DeepAgents source code
  • Architecture — The Architecture tool exposed by this server
  • Configuration — The Configuration tool exposed by this server

Adding it to your client

Installation goes through your MCP client rather than a global install: point it at langchain-mcp on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

When to reach for it

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Langchain's toolset — search_docs, search_langchain_code, search_langgraph_code and 3 more — is a fair guide to whether it matches your workflow. It is maintained by baixianger; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Langchain's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the langchain mcp server does with a few real requests.

Available tools

ToolWhat it does
search_docsSearch documentation, references, and tutorials
search_langchain_codeSearch LangChain source code
search_langgraph_codeSearch LangGraph source code
search_deepagents_codeSearch DeepAgents source code
ArchitectureThe Architecture tool exposed by this server.
ConfigurationThe Configuration tool exposed by this server.

How to install the Langchain MCP server

{
  "mcpServers": {
    "langchain": {
      "command": "npx",
      "args": ["-y", "langchain-mcp"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Langchain to search docs.
  • Use Langchain to search langchain code.
  • Use Langchain to search langgraph code.

Frequently asked questions

It connects Langchain to MCP-compatible AI assistants such as Claude and Cursor, exposing 6 tools (search_docs, search_langchain_code, search_langgraph_code, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Langchain directly.