Model Context Protocol (MCP) - Docs by LangChain中文

Model Context Protocol (MCP) 是一个开放协议，用于标准化应用向 LLM 提供工具和上下文的方式。LangChain 代理可以使用 @langchain/mcp-adapters 库调用 MCP 服务器上定义的工具。

快速开始

安装 @langchain/mcp-adapters 库：

npm install @langchain/mcp-adapters

@langchain/mcp-adapters 使代理能够使用一个或多个 MCP 服务器中定义的工具。

MultiServerMCPClient 默认是无状态的。每次工具调用都会创建新的 MCP ClientSession，执行工具，然后清理资源。

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: "http://localhost: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?" }],
});

使用 LangSmith 将 MCP 工具调用与代理的推理步骤一起追踪。按照 tracing quickstart 完成设置。

自定义服务器

如需创建自己的 MCP 服务器，可以使用 @modelcontextprotocol/sdk 库。该库提供了一种简单方式来定义 tools，并将其作为服务器运行。

npm install @modelcontextprotocol/sdk

如需使用 MCP 工具服务器测试代理，请使用以下示例：

数学服务器（stdio transport）

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 transport）

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 支持用于客户端和服务器通信的不同传输机制。

HTTP

http 传输方式（也称为 streamable-http）使用 HTTP 请求进行客户端和服务器通信。更多详情请参阅 MCP HTTP transport specification。

const client = new MultiServerMCPClient({
    weather: {
        transport: "sse",
        url: "http://localhost:8000/mcp",
    },
});

传递 headers

认证

stdio

客户端将服务器作为子进程启动，并通过标准输入/输出通信。该方式最适合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

Tools

Tools 允许 MCP 服务器暴露可执行函数，LLM 可以调用这些函数来执行操作，例如查询数据库、调用 API 或与外部系统交互。LangChain 会将 MCP tools 转换为 LangChain tools，使其可直接用于任何 LangChain 代理或工作流。

加载 tools

使用 client.getTools() 从 MCP 服务器获取 tools，并将其传给代理：

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 });

其他资源

Connect these docs to Claude, VSCode, and more via MCP for real-time answers.

Edit this page on GitHub or file an issue.

​快速开始

​自定义服务器

​传输方式

​HTTP

​传递 headers

​认证

​stdio

​核心功能

​Tools

​加载 tools

​其他资源

快速开始

自定义服务器

传输方式

HTTP

传递 headers

认证

stdio

核心功能

Tools

加载 tools

其他资源