mcp-use
mcp-use is a full-stack framework for the Model Context Protocol, offering MCP agents, clients, servers and a web-based inspector in both Python and TypeScript, with the pitch that you can get going in about six lines of code. The stack described in the README is MCP agents (AI agents that use tools and reason across steps), MCP clients (connect any LLM to any MCP server), MCP servers (build your own), an MCP Inspector (a web debugger) and MCP-UI resources for building ChatGPT apps with interactive widgets.
The quick start installs the package with pip (for example `pip install mcp-use langchain-openai`) and configures an MCPAgent with an MCPClient pointing at one or more servers, with equivalent TypeScript docs. The feature table shows agents, clients and the inspector available in both languages, while building MCP servers is available in TypeScript with Python marked as coming soon. There is also an MCP Cloud for deploying agents and servers, an online inspector, templates and documentation for each language. The licence is MIT.
Features
Why choose it
Trade-offs
Maintenance check
- Last commit
- 2026-10-21
- Commits, last 90 days
- 100+
- Releases, last 90 days
- 30
- Latest release
- [email protected] (2026-10-22)
- Open issues
- 102
- Recent issues with at least one comment
- 3/9
Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.
Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.
Compatibility
Quick start
Use cases
Alternatives
Comments
No comments yet. Be the first!