English|简体中文

🌐 Easy-MCP-Use is the open source TypeScript library to connect any LLM to any MCP server and build custom agents that have tool access, without using closed source or application clients.

💡 Let developers easily connect any LLM to tools like web browsing, file operations, and more with full TypeScript support.

Features

✨ Key Features

Quick start

With npm:

npm install easy-mcp-use

Or install from source:

git clone https://github.com/dforel/easy-mcp-use.git
cd easy-mcp-use
npm install
npm run build

Installing LangChain Providers

easy-mcp-use works with various LLM providers through LangChain. You'll need to install the appropriate LangChain provider package for your chosen LLM. For example:

# For OpenAI
npm install @langchain/openai

# For Anthropic
npm install @langchain/anthropic

# For other providers, check the [LangChain chat models documentation](https://js.langchain.com/docs/integrations/chat/)

and add your API keys for the provider you want to use to your .env file.

OPENAI_API_KEY=
ANTHROPIC_API_KEY=

Important: Only models with tool calling capabilities can be used with easy-mcp-use. Make sure your chosen model supports function calling or tool use.

Spin up your agent:

import { MCPClient } from 'easy-mcp-use';
import { MCPAgent, MCPAgentOptions } from 'easy-mcp-use';
import { ChatOpenAI } from '@langchain/openai';
import dotenv from 'dotenv';
dotenv.config();
 

const openAIApiKey = process.env.openRouteApiKey; 

if (!openAIApiKey) {
  throw new Error("openAIApiKey environment variable is not set");
}
console.log(`openAIApiKey: ${openAIApiKey}`);

async function main() {
    

  let config = {"mcpServers": {"http": {"url": "http://localhost:3001/sse"}}}
  // 从配置文件创建客户端
  const client = MCPClient.fromConfig( config );

  try { 
    const chat = new ChatOpenAI(
      {
        modelName: 'google/gemini-2.0-flash-exp:free', 
        streaming: true,
        openAIApiKey: openAIApiKey,
        configuration: {
          baseURL: 'https://openrouter.ai/api/v1',  
        }
      }
    );
    let options = {
      client: client,
      // verbose: true,
      maxSteps: 30, 
      llm:  chat,
    }
    let agent = new MCPAgent(options)

    let result = agent.run(
      `
      100 rmb can exchange how much doller？
      ` 
    );

     console.log( JSON.stringify(result) );
  } finally {
    // console.info('finally');
  }
}

main().catch(console.error);

You can also add the servers configuration from a config file like this:

const client = MCPClient.fromConfigFile(
    path.join(__dirname, 'browser_mcp.json')
);

Example configuration file (browser_mcp.json):

{
  "mcpServers": {
    "playwright": {
      "command": "npx",
      "args": ["@playwright/mcp@latest"],
      "env": {
        "DISPLAY": ":1"
      }
    }
  }
}

For other settings, models, and more, check out the documentation.

Example Use Cases

http server example

there have a example project: easy-mcp-use-example (https://github.com/dforel/easy-mcp-use-examples)

Web Browsing with Playwright

import { MCPClient } from '../src/client';
import path from 'path';
import { MCPAgent, MCPAgentOptions } from '../src/agents/mcpagent';
// import { ChatOpenAI } from 'langchain/core/language_models/chat_openai';
// import { OpenAI } from "@langchain/llms/openai";
import { ChatOpenAI } from '@langchain/openai';
import { logger } from '../src/logging';
import dotenv from 'dotenv';
dotenv.config();

const openAIApiKey = process.env.openAIApiKey; 
if (!openAIApiKey) {
  throw new Error("openAIApiKey environment variable is not set");
}
logger.info(`openAIApiKey: ${openAIApiKey}`);

async function main() {
  // 从配置文件创建客户端
  const client = await MCPClient.fromConfigFile(
    path.resolve(__dirname, './browser_mcp.json')
  );

  try { 
    const chat = new ChatOpenAI(
      {
        modelName: 'google/gemini-2.0-flash-exp:free', 
        // modelName: 'google/gemini-2.5-pro-exp-03-25:free', 
        streaming: true,
        openAIApiKey: openAIApiKey,
        configuration: {
          baseURL: 'https://openrouter.ai/api/v1',  
        }
      }
    );
    let options: MCPAgentOptions = {
      client: client,
      verbose: true,
      maxSteps: 30, 
      llm:  chat,
    }
    let agent = new MCPAgent(options)

    let result = agent.run(
      `
      open bing.com
      click input
      input easy-mcp-use
      click search
      ` 
    );

     console.log( JSON.stringify(result) );
  } finally {
    console.info('finally');
  }
}

main().catch(console.error);

This example demonstrates how to connect to an MCP server running on a specific HTTP port. Make sure to start your MCP server before running this example.

Multi-Server Support

MCP-Use-TS allows configuring and connecting to multiple MCP servers simultaneously using the MCPClient. This enables complex workflows that require tools from different servers, such as web browsing combined with file operations or 3D modeling.

Configuration

You can configure multiple servers in your configuration file:

{
  "mcpServers": {
    "airbnb": {
      "command": "npx",
      "args": ["-y", "@openbnb/mcp-server-airbnb", "--ignore-robots-txt"]
    },
    "playwright": {
      "command": "npx",
      "args": ["@playwright/mcp@latest"],
      "env": {
        "DISPLAY": ":1"
      }
    }
  }
}

Usage

The MCPClient class provides methods for managing connections to multiple servers. When creating an MCPAgent, you can provide an MCPClient configured with multiple servers.

By default, the agent will have access to tools from all configured servers. If you need to target a specific server for a particular task, you can specify the serverName when calling the agent.run() method.

// Example: Manually selecting a server for a specific task
const airbnbResult = await agent.run(
    'Search for Airbnb listings in Barcelona',
    { serverName: 'airbnb' } // Explicitly use the airbnb server
);

const googleResult = await agent.run(
    'Find restaurants near the first result using Google Search',
    { serverName: 'playwright' } // Explicitly use the playwright server
);

Agent-Specific Verbosity

If you only want to see debug information from the agent without enabling full debug logging, you can set the verbose parameter when creating an MCPAgent:

// Create agent with increased verbosity
const agent = new MCPAgent({
    llm,
    client,
    verbose: true  // Only shows debug messages from the agent
});

This is useful when you only need to see the agent's steps and decision-making process without all the low-level debug information from other components.

Roadmap

Contributing

We love contributions! Feel free to open issues for bugs or feature requests.

Requirements

• Node.js 18+
• TypeScript 5.0+
• MCP implementation (like Playwright MCP)
• LangChain and appropriate model libraries (OpenAI, Anthropic, etc.)

Citation

If you use MCP-Use-TS in your research or project, please cite:

@software{easy-mcp-use,
  author = {dforel},
  title = {Easy-MCP-Use: MCP Library for TypeScript},
  year = {2025},
  publisher = {GitHub},
  url = {https://github.com/dforel/easy-mcp-use}
}

Other

this project is a fork of mcp-use

i hope you enjoy it

License

MIT