模型上下文协议 (MCP) 是一种开放协议，用于标准化应用程序如何向大模型 (LLM) 提供工具和上下文。LangChain 智能体可以使用文档索引
在以下地址获取完整的文档索引：https://docs.langchain.org.cn/llms.txt
在进一步探索之前，请使用此文件发现所有可用页面。
@langchain/mcp-adapters 库来使用 MCP 服务器定义的工具。
快速入门
安装@langchain/mcp-adapters 库
npm install @langchain/mcp-adapters
@langchain/mcp-adapters 使智能体能够使用在一个或多个 MCP 服务器上定义的工具。
MultiServerMCPClient 默认是无状态的。每次工具调用都会创建一个新的 MCP ClientSession，执行工具，然后进行清理。访问多个 MCP 服务器
import { MultiServerMCPClient } from "@langchain/mcp-adapters";
import { ChatAnthropic } from "@langchain/anthropic";
import { createAgent } from "langchain";
const client = new MultiServerMCPClient({
math: {
transport: "stdio", // Local subprocess communication
command: "node",
// Replace with absolute path to your math_server.js file
args: ["/path/to/math_server.js"],
},
weather: {
transport: "http", // HTTP-based remote server
// Ensure you start your weather server on port 8000
url: "https://:8000/mcp",
},
});
const tools = await client.getTools();
const agent = createAgent({
model: "claude-sonnet-4-6",
tools,
});
const mathResponse = await agent.invoke({
messages: [{ role: "user", content: "what's (3 + 5) x 12?" }],
});
const weatherResponse = await agent.invoke({
messages: [{ role: "user", content: "what is the weather in nyc?" }],
});
自定义服务器
要创建自己的 MCP 服务器，可以使用@modelcontextprotocol/sdk 库。该库提供了一种简单的方式来定义 工具 并将其作为服务器运行。
npm install @modelcontextprotocol/sdk
数学服务器 (stdio 传输)
import { Server } from "@modelcontextprotocol/sdk/server/index.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
import {
CallToolRequestSchema,
ListToolsRequestSchema,
} from "@modelcontextprotocol/sdk/types.js";
const server = new Server(
{
name: "math-server",
version: "0.1.0",
},
{
capabilities: {
tools: {},
},
}
);
server.setRequestHandler(ListToolsRequestSchema, async () => {
return {
tools: [
{
name: "add",
description: "Add two numbers",
inputSchema: {
type: "object",
properties: {
a: {
type: "number",
description: "First number",
},
b: {
type: "number",
description: "Second number",
},
},
required: ["a", "b"],
},
},
{
name: "multiply",
description: "Multiply two numbers",
inputSchema: {
type: "object",
properties: {
a: {
type: "number",
description: "First number",
},
b: {
type: "number",
description: "Second number",
},
},
required: ["a", "b"],
},
},
],
};
});
server.setRequestHandler(CallToolRequestSchema, async (request) => {
switch (request.params.name) {
case "add": {
const { a, b } = request.params.arguments as { a: number; b: number };
return {
content: [
{
type: "text",
text: String(a + b),
},
],
};
}
case "multiply": {
const { a, b } = request.params.arguments as { a: number; b: number };
return {
content: [
{
type: "text",
text: String(a * b),
},
],
};
}
default:
throw new Error(`Unknown tool: ${request.params.name}`);
}
});
async function main() {
const transport = new StdioServerTransport();
await server.connect(transport);
console.error("Math MCP server running on stdio");
}
main();
天气服务器 (SSE 传输)
import { Server } from "@modelcontextprotocol/sdk/server/index.js";
import { SSEServerTransport } from "@modelcontextprotocol/sdk/server/sse.js";
import {
CallToolRequestSchema,
ListToolsRequestSchema,
} from "@modelcontextprotocol/sdk/types.js";
import express from "express";
const app = express();
app.use(express.json());
const server = new Server(
{
name: "weather-server",
version: "0.1.0",
},
{
capabilities: {
tools: {},
},
}
);
server.setRequestHandler(ListToolsRequestSchema, async () => {
return {
tools: [
{
name: "get_weather",
description: "Get weather for location",
inputSchema: {
type: "object",
properties: {
location: {
type: "string",
description: "Location to get weather for",
},
},
required: ["location"],
},
},
],
};
});
server.setRequestHandler(CallToolRequestSchema, async (request) => {
switch (request.params.name) {
case "get_weather": {
const { location } = request.params.arguments as { location: string };
return {
content: [
{
type: "text",
text: `It's always sunny in ${location}`,
},
],
};
}
default:
throw new Error(`Unknown tool: ${request.params.name}`);
}
});
app.post("/mcp", async (req, res) => {
const transport = new SSEServerTransport("/mcp", res);
await server.connect(transport);
});
const PORT = process.env.PORT || 8000;
app.listen(PORT, () => {
console.log(`Weather MCP server running on port ${PORT}`);
});
传输方式
MCP 支持多种用于客户端-服务器通信的传输机制。HTTP
http 传输（也称为 streamable-http）使用 HTTP 请求进行客户端-服务器通信。更多详情请参阅 MCP HTTP 传输规范。
const client = new MultiServerMCPClient({
weather: {
transport: "sse",
url: "https://:8000/mcp",
},
});
传递请求头
身份验证
stdio
客户端将服务器作为子进程启动，并通过标准输入/输出进行通信。适用于本地工具和简单设置。const client = new MultiServerMCPClient({
math: {
transport: "stdio",
command: "node",
args: ["/path/to/math_server.js"],
},
});
核心功能
工具
工具 允许 MCP 服务器公开可执行函数，供大模型调用以执行操作，例如查询数据库、调用 API 或与外部系统交互。LangChain 会将 MCP 工具转换为 LangChain 工具，使其可以直接用于任何 LangChain 智能体或工作流中。加载工具
使用client.getTools() 从 MCP 服务器检索工具并将其传递给您的智能体
import { MultiServerMCPClient } from "@langchain/mcp-adapters";
import { createAgent } from "langchain";
const client = new MultiServerMCPClient({...});
const tools = await client.getTools();
const agent = createAgent({ model: "claude-sonnet-4-6", tools });
附加资源
将这些文档连接到 Claude、VSCode 等，以获得实时答案。