mcp-use
A full-stack MCP framework for building MCP applications and servers for ChatGPT, Claude, and other AI agents.
- Type
- MCP
- Transport
- http
- Open source
- Yes
- GitHub Stars
- ★ 10.1k
- Source
- mcp-github
- Repository
- github.com/mcp-use/mcp-use
Overview
mcp-use is a full-stack MCP framework designed to build MCP applications and servers compatible with ChatGPT, Claude, and other AI agents. It provides SDKs (supporting TypeScript and Python) to help developers quickly create and deploy MCP servers and applications. With mcp-use, AI agents can easily gain new capabilities and tools, enhancing their interactivity and practicality. Ideal for developers looking to extend the functionality of AI agents.
Capabilities
- ▪Create MCP servers
- ▪Build MCP applications
- ▪Test and debug MCP services
- ▪One-click deployment of MCP projects
Use cases
Setup
npx create-mcp-use-app@latest or pip install mcp_use
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
Which languages does mcp-use support?
Currently supports TypeScript and Python.
How do I get started with mcp-use?
Install via npx or pip, then follow the quick start guide in the documentation.
Related skills
gemini-cli
Gemini CLI is an open-source AI agent that brings Gemini's powerful capabilities directly into the terminal.
private-gpt
Provides a complete API layer for local models, supporting RAG, skills, tools, and more.
planning-with-files
File-based persistent planning skill, ideal for AI coding agents and long-running tasks.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.