https://github.com/mcp-use/mcp-use-ts
🚀 mcp-use is a TypeScript library that makes it easy to connect LangChain.js-compatible LLMs with MCP servers. Build powerful, flexible AI agents with dynamic tool access and multi-server support.
https://github.com/mcp-use/mcp-use-ts
agent langchain llm mcp mcp-client mcp-server typescript
Last synced: 4 months ago
JSON representation
🚀 mcp-use is a TypeScript library that makes it easy to connect LangChain.js-compatible LLMs with MCP servers. Build powerful, flexible AI agents with dynamic tool access and multi-server support.
- Host: GitHub
- URL: https://github.com/mcp-use/mcp-use-ts
- Owner: mcp-use
- License: mit
- Created: 2025-04-20T08:42:35.000Z (7 months ago)
- Default Branch: main
- Last Pushed: 2025-06-28T17:46:54.000Z (4 months ago)
- Last Synced: 2025-06-28T18:06:09.237Z (4 months ago)
- Topics: agent, langchain, llm, mcp, mcp-client, mcp-server, typescript
- Language: TypeScript
- Homepage:
- Size: 535 KB
- Stars: 28
- Watchers: 1
- Forks: 6
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
Unified MCP Client Library
🌐 **MCP Client** is the open-source way to connect **any LLM to any MCP server** in TypeScript/Node.js, letting you build custom agents with tool access without closed-source dependencies.
💡 Let developers easily connect any LLM via LangChain.js to tools like web browsing, file operations, 3D modeling, and more.
---
## ✨ Key Features
| Feature | Description |
| ------------------------------- | -------------------------------------------------------------------------- |
| 🔄 **Ease of use** | Create an MCP-capable agent in just a few lines of TypeScript. |
| 🤖 **LLM Flexibility** | Works with any LangChain.js-supported LLM that supports tool calling. |
| 🌐 **HTTP Support** | Direct SSE/HTTP connection to MCP servers. |
| ⚙️ **Dynamic Server Selection** | Agents select the right MCP server from a pool on the fly. |
| 🧩 **Multi-Server Support** | Use multiple MCP servers in one agent. |
| 🛡️ **Tool Restrictions** | Restrict unsafe tools like filesystem or network. |
| 🔧 **Custom Agents** | Build your own agents with LangChain.js adapter or implement new adapters. |
---
## 🚀 Quick Start
### Requirements
- Node.js 22.0.0 or higher
- npm, yarn, or pnpm (examples use pnpm)
### Installation
```bash
# Install from npm
npm install mcp-use
# LangChain.js and your LLM provider (e.g., OpenAI)
npm install langchain @langchain/openai dotenv
```
Create a `.env`:
```ini
OPENAI_API_KEY=your_api_key
```
### Basic Usage
```ts
import { ChatOpenAI } from '@langchain/openai'
import { MCPAgent, MCPClient } from 'mcp-use'
import 'dotenv/config'
async function main() {
// 1. Configure MCP servers
const config = {
mcpServers: {
playwright: { command: 'npx', args: ['@playwright/mcp@latest'] }
}
}
const client = MCPClient.fromDict(config)
// 2. Create LLM
const llm = new ChatOpenAI({ modelName: 'gpt-4o' })
// 3. Instantiate agent
const agent = new MCPAgent({ llm, client, maxSteps: 20 })
// 4. Run query
const result = await agent.run('Find the best restaurant in Tokyo using Google Search')
console.log('Result:', result)
}
main().catch(console.error)
```
---
## 📂 Configuration File
You can store servers in a JSON file:
```json
{
"mcpServers": {
"playwright": {
"command": "npx",
"args": ["@playwright/mcp@latest"]
}
}
}
```
Load it:
```ts
import { MCPClient } from 'mcp-use'
const client = MCPClient.fromConfigFile('./mcp-config.json')
```
---
## 📚 Examples
We provide a comprehensive set of examples demonstrating various use cases. All examples are located in the `examples/` directory with a dedicated README.
### Running Examples
```bash
# Install dependencies
npm install
# Run any example
npm run example:airbnb # Search accommodations with Airbnb
npm run example:browser # Browser automation with Playwright
npm run example:chat # Interactive chat with memory
npm run example:filesystem # File system operations
npm run example:http # HTTP server connection
npm run example:everything # Test MCP functionalities
npm run example:multi # Multiple servers in one session
```
### Example Highlights
- **Browser Automation**: Control browsers to navigate websites and extract information
- **File Operations**: Read, write, and manipulate files through MCP
- **Multi-Server**: Combine multiple MCP servers (Airbnb + Browser) in a single task
- **Sandboxed Execution**: Run MCP servers in isolated E2B containers
- **OAuth Flows**: Authenticate with services like Linear using OAuth2
See the [examples README](./examples/README.md) for detailed documentation and prerequisites.
---
## 🔄 Multi-Server Example
```ts
const config = {
mcpServers: {
airbnb: { command: 'npx', args: ['@openbnb/mcp-server-airbnb'] },
playwright: { command: 'npx', args: ['@playwright/mcp@latest'] }
}
}
const client = MCPClient.fromDict(config)
const agent = new MCPAgent({ llm, client, useServerManager: true })
await agent.run('Search Airbnb in Barcelona, then Google restaurants nearby')
```
---
## 🔒 Tool Access Control
```ts
const agent = new MCPAgent({
llm,
client,
disallowedTools: ['file_system', 'network']
})
```
## 👥 Contributors
## 📜 License
MIT © [Zane](https://github.com/zandko)
