LangChain.js MCP Adapters

This library provides a lightweight wrapper that makesAnthropic Model Context Protocol (MCP) tools compatible with LangChain.js and LangGraph.js.

Features

🔌 Transport Options
- Connect to MCP servers via stdio (local) or SSE (remote)
- Support for custom headers in SSE connections for authentication
- Configurable reconnection strategies for both transport types
🔄 Multi-Server Management
- Connect to multiple MCP servers simultaneously
- Auto-organize tools by server or access them as a flattened collection
- Convenient configuration via JSON file
🧩 Agent Integration
- Compatible with LangChain.js and LangGraph.js
- Optimized for OpenAI, Anthropic, and Google models
🛠️ Development Features
- Flexible configuration options
- Robust error handling

Installation

npm install @langchain/mcp-adapters

Optional Dependencies

For SSE connections with custom headers in Node.js:

npm install eventsource

For enhanced SSE header support:

npm install extended-eventsource

Prerequisites

Node.js >= 18
For stdio transport: Python MCP servers require Python 3.8+
For SSE transport: A running MCP server with SSE endpoint
For SSE with headers in Node.js: The eventsource package

Quickstart

Here is a simple example of using the MCP tools with a LangGraph agent.

npm install @langchain/mcp-adapters @langchain/langgraph @langchain/core @langchain/openai

export OPENAI_API_KEY=<your_api_key>

Server

First, let's create an MCP server that can add and multiply numbers.

# math_server.py
from mcp.server.fastmcp import FastMCP

mcp = FastMCP("Math")

@mcp.tool()
def add(a: int, b: int) -> int:
    """Add two numbers"""
    return a + b

@mcp.tool()
def multiply(a: int, b: int) -> int:
    """Multiply two numbers"""
    return a * b

if __name__ == "__main__":
    mcp.run(transport="stdio")

Client

import { Client } from '@modelcontextprotocol/sdk/client/index.js';
import { StdioClientTransport } from '@modelcontextprotocol/sdk/client/stdio.js';
import { ChatOpenAI } from '@langchain/openai';
import { createReactAgent } from '@langchain/langgraph/prebuilt';
import { loadMcpTools } from '@langchain/mcp-adapters';

// Initialize the ChatOpenAI model
const model = new ChatOpenAI({ modelName: 'gpt-4' });

// Create transport for stdio connection
const transport = new StdioClientTransport({
  command: 'python',
  args: ['math_server.py'],
});

// Initialize the client
const client = new Client({
  name: 'math-client',
  version: '1.0.0',
});

try {
  // Connect to the transport
  await client.connect(transport);

  // Get tools
  const tools = await loadMcpTools("math", client);

  // Create and run the agent
  const agent = createReactAgent({ llm: mo

Categories

Current Category: agent-tools

CyberSecurity-MCPs

langchainjs-mcp-adapters