🤖 LangChain MCP API

具有多提供商LLM支持的高性能Go实现

](https://golang.org) ![Fiber](https://gofiber.io) ![License](LICENSE) ](https://hub.docker.com)

*通用LangChain服务器支持OpenAI、Claude、Ollama、Llama.cpp等，并集成MCP工具*

______________________________________________________________________

✨ 特性

🚀 多个LLM提供商

OpenAI （GPT-4、GPT-3.5、GPT-4o）
克劳德 （人类学）
开放路由 （100+型号）
奥拉玛 （本地模型）
Llama.cpp （GGUF型号）
vLLM （高性能推理）

🔧 高级功能

MCP工具 -动态刀具加载
流媒体 -实时SSE响应
代理系统 -自主任务执行
上下文管理 -智能历史修剪
详细日志 -详细的执行痕迹

______________________________________________________________________

🐳 码头工人

选项1：从Docker Hub拉取（推荐）

从Docker Hub中提取预构建映像：

# Pull the latest image
docker pull jefriherditriyanto/langchain-mcp-api:latest

# Run container
docker run -d \
  --name langchain-mcp-api \
  -p 6000:6000 \
  jefriherditriyanto/langchain-mcp-api:latest

使用Docker Compose：

version: '3.8'
services:
  langchain-mcp-api:
    image: jefriherditriyanto/langchain-mcp-api:latest
    container_name: langchain-mcp-api
    ports:
      - "6000:6000"
    environment:
      - PORT=6000
    restart: unless-stopped

运行方式：

docker-compose up -d

______________________________________________________________________

📡 API文档

基础URL

http://localhost:6000

端点

1️⃣ 你好，世界

GET /

答复：

{
  "message": "🤖 LangChain MCP API is running",
  "version": "1.0.0"
}

______________________________________________________________________

2️⃣ 健康检查

GET /health

答复：

{
  "status": "ok"
}

______________________________________________________________________

3️⃣ 聊天（非流媒体）

POST /chat

请求正文：

{
  "credential": {
    "provider": "openai",
    "api_key": "sk-...",
    "model": "gpt-4o-mini",
    "set": {
      "temperature": 0.7,
      "max_tokens": 2000
    }
  },
  "system_prompt": "You are a helpful assistant",
  "input": "tolong cari dns lookup dari www.example.com, sajikan dalam bahasa indonesia",
  "servers": ["http://host.docker.internal:4050"] // this tool available on "MCP Server: Python"
}

答复：

{
  "messages": [
    {
      "role": "user",
      "content": "tolong cari dns lookup dari www.example.com, sajikan dalam bahasa indonesia"
    },
    {
      "role": "assistant",
      "content": "{\"tool_name\":\"network_dns_lookup\",\"tool_args\":{\"hostname\":\"www.example.com\"}}",
      "tool_calls": [
        {
          "id": "manual_1770445792732616000",
          "name": "network_dns_lookup",
          "args": {
            "hostname": "www.example.com"
          },
          "type": "tool_call"
        }
      ],
      "response_metadata": {
        "finish_reason": "stop",
        "model_provider": "openai",
        "model_name": "gpt-4o-mini",
        "usage": null,
        "system_fingerprint": ""
      },
      "usage_metadata": {
        "output_tokens": 120,
        "input_tokens": 1382,
        "total_tokens": 1502
      }
    },
    {
      "role": "tool",
      "content": "Tool 'network_dns_lookup' SUCCESS: {\"hostname\":\"www.example.com\",\"ip\":\"104.18.26.120\"}",
      "tool_call_id": "manual_1770445792732616000",
      "name": "network_dns_lookup"
    },
    {
      "role": "assistant",
      "content": "Berikut hasil **DNS lookup** untuk `www.example.com`:\n\n- **Nama Domain**: www.example.com  \n- **Alamat IP (IPv4)**: 104.18.26.120  \n\n### Penjelasan:\nDNS (Domain Name System) berfungsi untuk mengubah nama domain (seperti `www.example.com`) menjadi alamat IP (seperti `104.18.26.120`) yang digunakan oleh komputer untuk mengakses situs web.",
      "response_metadata": {
        "finish_reason": "stop",
        "model_provider": "openai",
        "model_name": "gpt-4o-mini",
        "usage": null,
        "system_fingerprint": ""
      },
      "usage_metadata": {
        "output_tokens": 611,
        "input_tokens": 84,
        "total_tokens": 695
      }
    }
  ],
  "message": "Berikut hasil **DNS lookup** untuk `www.example.com`:\n\n- **Nama Domain**: www.example.com  \n- **Alamat IP (IPv4)**: 104.18.26.120  \n\n### Penjelasan:\nDNS (Domain Name System) berfungsi untuk mengubah nama domain (seperti `www.example.com`) menjadi alamat IP (seperti `104.18.26.120`) yang digunakan oleh komputer untuk mengakses situs web.",
  "usage_metadata": {
    "output_tokens": 731,
    "input_tokens": 1466,
    "total_tokens": 2197
  },
  "model_provider": "openai",
  "model_name": "gpt-4o-mini",
  "finish_reason": "stop",
  "total_iterations": 2,
  "tool_calls_count": 1,
  "execution_time_ms": 26818,
  "execution_time_sec": 26.818,
  "tokens_per_second": 81.92
}

______________________________________________________________________

4️⃣ 聊天流（SSE）

POST /chat/stream

请求正文： *（与 /chat)*

答复： 服务器发送的事件流

data: {"type":"start","timestamp":"2024-02-04T09:00:00Z","input":"What is the weather?"}

data: {"type":"servers_checked","available_servers":["http://host.docker.internal:4000"],"total_servers":1}

data: {"type":"thinking_start","timestamp":"2024-02-04T09:00:01Z"}

data: {"type":"thinking_chunk","chunk":"I need to check the weather...","is_final":false}

data: {"type":"message_start","timestamp":"2024-02-04T09:00:02Z"}

data: {"type":"message_chunk","chunk":"The weather is ","is_final":false}

data: {"type":"message_chunk","chunk":"sunny, 28°C","is_final":true}

data: {"type":"done","done":true,"total_steps":3,"timestamp":"2024-02-04T09:00:03Z"}

______________________________________________________________________

⚙️ 配置

提供商设置

提供者	密钥	必填字段
OpenAI	`openai`	`api_key`, `model`
克劳德	`claude`	`api_key`, `model`
开放路由	`openrouter`	`api_key`, `model`
奥拉玛	`ollama`	`url`, `model`
Llama.cpp	`llama_cpp`	`url`, `model`
vLLM	`vllm`	`url`, `model`

高级设置

{
  "set": {
    "temperature": 0.7,           // Creativity (0.0 - 2.0)
    "max_tokens": 1000,           // Max response length
    "top_p": 0.9,                 // Nucleus sampling
    "frequency_penalty": 0.0,     // Repetition penalty
    "presence_penalty": 0.0,      // Topic diversity
    "max_context_messages": 4     // History window size
  }
}

______________________________________________________________________

� MCP服务器示例

构建您自己的MCP（模型上下文协议）服务器，为LangChain MCP API提供自定义工具。

完整示例

完整的工作示例可在以下网址获得：

mcp服务器bunts express -BunTS/Express实施
mcp服务器golang gofiber -Golang/GoFiber实施
mcp服务器python fastapi -Python/FastAPI实现
mcp服务器php代码点火器 -PHP（FrankenPHP）/CodeIgniter实现
mcp服务器php-laravel -PHP（FrankenPHP）/Laravel实现
马上就来。..（Rust、Java、Kotlin、C#、Ruby、无服务器、N8N、Node Red）

快速开始

# Clone MCP server example
git clone https://github.com/jefripunza/langchain-mcp-api/tree/master/mcp-server-bunts-express

# Navigate to MCP server example
cd mcp-server-bunts-express

# Install dependencies
bun install

# Run the server
bun run dev

服务器将在以下时间启动 http://localhost:4000 🎉

______________________________________________________________________

项目结构

mcp-server-bunts-express/
├── src/
│   ├── index.ts         # Main server
│   ├── registry.ts      # Tool registry
│   └── tools/
│       ├── math.ts      # Math tools
│       └── weather.ts   # Weather tools
├── package.json
└── tsconfig.json

______________________________________________________________________

实施指南

1️⃣ 主服务器 (`src/index.ts`)

import express from "express";
import cors from "cors";
import helmet from "helmet";
import morgan from "morgan";

import { tools, findTool } from "./registry";

const app = express();
app.use(express.json());
app.use(cors());
app.use(helmet());

app.listen(4000, () => {
  console.log("🧠 MCP Server running on http://localhost:4000");
});
app.use(morgan("dev"));

// REQUIRED!
app.get("/health", (_req, res) => res.json({ status: "ok" }));

// MCP-style: list tools, REQUIRED!
app.get("/mcp/tools", (_req, res) => {
  res.json(
    tools.map((t) => ({
      name: t.name,
      description: t.description,
      parameters: t.parameters,
    })),
  );
});

// MCP-style: invoke tool, REQUIRED!
app.post("/mcp/invoke", async (req, res) => {
  const { name, arguments: args } = req.body;
  const tool = findTool(name);

  if (!tool) {
    return res.status(404).json({ error: "Tool not found" });
  }
  if (!tool.handler) {
    return res.status(400).json({ error: "Tool handler not found" });
  }

  const result = await tool.handler(args);
  res.json(result);
});

______________________________________________________________________

2️⃣ 工具注册表 (`src/registry.ts`)

import type { Tool } from "./types/tool";
import { mathTools } from "./tools/math";
import { weatherTools } from "./tools/weather";

export const tools: Tool[] = [...mathTools, ...weatherTools];

export function findTool(name: string) {
  return tools.find((t) => t.name === name);
}

______________________________________________________________________

3️⃣ 数学工具示例 (`src/tools/math.ts`)

import type { Tool } from "../types/tool";

export const mathTools: Tool[] = [
  {
    name: "add",
    description: "Add two numbers together", // add to main prompt, please detail!
    // add to main prompt, please detail!
    parameters: {
      type: "object",
      properties: {
        a: { type: "number" },
        b: { type: "number" },
      },
      required: ["a", "b"],
    },
    // as controller / logic base
    handler: async ({ a, b }: { a: number; b: number }) => {
      console.log(`✅ MCP1 Math: ${a}+${b}=${a + b}`);
      return { result: a + b };
    },
  },
];

______________________________________________________________________

4️⃣ 天气工具示例 (`src/tools/weather.ts`)

import { fetchWeatherApi } from "openmeteo";
import type { Tool } from "../types/tool";

// advance tool version
export const weatherTools: Tool[] = [
  {
    name: "getWeather",
    description: "Get weather data by coordinates",
    parameters: {
      type: "object",
      properties: {
        latitude: { type: "number" },
        longitude: { type: "number" },
      },
      required: ["latitude", "longitude"],
    },
    handler: async ({
      latitude,
      longitude,
    }: {
      latitude: number;
      longitude: number;
    }) => {
      const params = {
        latitude,
        longitude,
        hourly: ["temperature_2m", "relative_humidity_2m", "rain"],
        timezone: "auto",
      };
      
      const responses = await fetchWeatherApi(
        "https://api.open-meteo.com/v1/forecast",
        params
      );
      
      const response = responses[0];
      const hourly = response.hourly()!;
      
      console.log(`✅ MCP1 Weather: ${latitude}, ${longitude}`);
      return {
        latitude,
        longitude,
        temperature: hourly.variables(0)!.valuesArray(),
        humidity: hourly.variables(1)!.valuesArray(),
        rain: hourly.variables(2)!.valuesArray(),
      };
    },
  },
];

______________________________________________________________________

MCP协议端点

您的MCP服务器必须实现这三个非常必要的端点：

端点	方法	描述
`/health`	GET	健康检查
`/mcp/tools`	GET	列出所有可用工具
`/mcp/invoke`	POST	执行特定工具

______________________________________________________________________

测试您的MCP服务器

# List available tools
curl http://localhost:4000/mcp/tools

# Invoke math tool
curl -X POST http://localhost:4000/mcp/invoke \
  -H "Content-Type: application/json" \
  -d '{
    "name": "add",
    "arguments": {"a": 5, "b": 3}
  }'

# Invoke weather tool
curl -X POST http://localhost:4000/mcp/invoke \
  -H "Content-Type: application/json" \
  -d '{
    "name": "getWeather",
    "arguments": {"latitude": -6.2, "longitude": 106.8}
  }'

______________________________________________________________________

与LangChain MCP API一起使用

MCP服务器运行后，将其与LangChain MCP API一起使用：

curl -X POST http://localhost:6000/chat \
  -H "Content-Type: application/json" \
  -d '{
    "credential": {
      "provider": "openai",
      "api_key": "sk-...",
      "model": "gpt-4o-mini"
    },
    "input": "What is 25 + 37?",
    "servers": ["http://host.docker.internal:4000"]
  }'

LangChain MCP API将自动：

从您的MCP服务器发现工具
让LLM决定使用哪些工具
执行工具并返回结果

______________________________________________________________________

🔍 详细日志

使用控制详细的执行日志 VERBOSE 环境变量：

启用详细模式

# Enable verbose logging (shows all requestID-prefixed logs)
export VERBOSE=true
go run main.go

# Or with Docker
docker run -d \
  -p 6000:6000 \
  -e VERBOSE=true \
  jefriherditriyanto/langchain-mcp-api:latest

禁用详细模式

# Disable verbose logging (hides requestID-prefixed logs)
export VERBOSE=false
go run main.go

# Or simply don't set the variable (defaults to false)
go run main.go

详细输出示例

当 VERBOSE=true，您将看到详细的执行痕迹：

[1kqlh2PxHZZvLVLiBbdbWfdXQ9] [START REQUEST]
[1kqlh2PxHZZvLVLiBbdbWfdXQ9]📦 [AGENT] Creating LangChain Agent...
[1kqlh2PxHZZvLVLiBbdbWfdXQ9]   Provider: llama_cpp
[1kqlh2PxHZZvLVLiBbdbWfdXQ9]   Model: gpt-oss-20b.gguf
[1kqlh2PxHZZvLVLiBbdbWfdXQ9]   ✅ Loaded 22 tools from MCP servers

[1kqlh2PxHZZvLVLiBbdbWfdXQ9]🚀 [INVOKE] Starting agent invocation...
[1kqlh2PxHZZvLVLiBbdbWfdXQ9]   Input: What is the weather?

[1kqlh2PxHZZvLVLiBbdbWfdXQ9]   🔁 [ITERATION 1/10]
[1kqlh2PxHZZvLVLiBbdbWfdXQ9]      📝 Built 2 messages for LLM
[1kqlh2PxHZZvLVLiBbdbWfdXQ9]      🤖 Calling LLM...
[1kqlh2PxHZZvLVLiBbdbWfdXQ9]      ✅ LLM Response (245 chars)
[1kqlh2PxHZZvLVLiBbdbWfdXQ9]      🔧 Detected 1 tool call(s)
[1kqlh2PxHZZvLVLiBbdbWfdXQ9]         1. getWeather({"lat": -7.7, "lon": 109.0})
[1kqlh2PxHZZvLVLiBbdbWfdXQ9]      ⚙️  Executing tools...
[1kqlh2PxHZZvLVLiBbdbWfdXQ9]         [1/1] Executing: getWeather
[1kqlh2PxHZZvLVLiBbdbWfdXQ9]            ✅ Success from http://host.docker.internal:4000
[1kqlh2PxHZZvLVLiBbdbWfdXQ9]      ✅ Tools executed successfully (1 results)

[1kqlh2PxHZZvLVLiBbdbWfdXQ9] ✅ [INVOKE] Agent invocation completed

______________________________________________________________________

🐛 故障排除

Error: "No MCP servers available"

确保MCP服务器正在运行
检查服务器URL是否正确
验证健康端点： curl http://localhost:4000/health

Error: "Missing api key"

验证请求中是否设置了API密钥
检查API密钥格式是否正确
确保提供程序名称匹配

Error: "Context size exceeded"

减少 max_context_messages （默认值：4）
使用较短的系统提示
启用响应截断

Streaming not working

确保客户端支持服务器发送的事件
检查网络/代理设置
使用 -N 带有卷曲的旗帜，用于流媒体播放

______________________________________________________________________

📊 演出

度量	值
启动时间	\<1s
内存使用	~50MB（空闲）
并发请求	1000+
响应时间	\<100ms（无LLM）

______________________________________________________________________

📄 许可证

MIT许可证-请参阅许可证详细信息文件

______________________________________________________________________

👥 贡献者

杰弗里·赫迪·特里扬托 (@jefripunza)

______________________________________________________________________

🔗 相关项目

MCP服务器 -模型上下文协议服务器实现
LangChain Go -官方LangChain Go库

______________________________________________________________________

⭐ 如果你觉得这个仓库有用，就把它标上！

由...制作❤️ 使用去和纤维

Langchain MCP API

快速接入

详细介绍