mcp-use-ts
by mcp-use·★ 174·Score 47
Complete TypeScript framework for MCP with client/server SDKs, React hooks, and built-in debugging tools.
Overview
MCP-Use is a comprehensive TypeScript framework that provides everything needed to build AI agents using MCP servers. It includes both client and server SDKs, React hooks for UI widgets, and a built-in inspector for debugging. The framework offers hot reload capabilities, automatic server management, support for multiple MCP servers, and OAuth handling. It's designed to provide the best developer experience with TypeScript-first development and production-ready builds.
Try asking AI
After installing, here are 5 things you can ask your AI assistant:
When to choose this
Choose MCP-Use when you're building TypeScript-based MCP applications that require rich UI components, debugging capabilities, and a comprehensive development framework.
When NOT to choose this
Avoid if you need minimal dependencies or are building a simple MCP server without UI components, as MCP-Use provides a full-featured framework with more overhead.
Tools this server exposes
1 tool extracted from the README (low confidence)get_weatherget_weather({ city: string, units?: 'celsius' | 'fahrenheit' })Get current weather for a city
Note: The README shows example code defining MCP tools with 'server.tool()' but doesn't list specific tools. The 'get_weather' example is the only concrete tool definition visible.
Comparable tools
Installation
Installation
Quick Start
# Create a new MCP application
npx create-mcp-use-app my-mcp-app
# Navigate to your project
cd my-mcp-app
# Start development
npm run devUsing with Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"mcp-use": {
"command": "npx",
"args": ["-y", "@mcp-use/cli", "dev"]
}
}
}FAQ
- What makes MCP-Use different from other MCP frameworks?
- MCP-Use provides a complete ecosystem with both client and server SDKs, built-in debugging inspector, React widget support, and hot reload capabilities. It's designed specifically for TypeScript development with a focus on developer experience.
- Can I use MCP-Use with any LLM provider?
- Yes, MCP-Use is LLM agnostic and works with OpenAI, Anthropic, Google, or any LangChain-supported LLM. It provides adapters to integrate with various AI SDKs.
Compare mcp-use-ts with
Last updated · Auto-generated from public README + GitHub signals.