Documentation Index
Fetch the complete documentation index at: https://mintlify.com/mcp-use/mcp-use/llms.txt
Use this file to discover all available pages before exploring further.
Package Installation
Install mcp-use for Python using your preferred package manager:Installing LangChain Providers
mcp-use works with various LLM providers through LangChain. You’ll need to install the appropriate LangChain provider package for your chosen LLM:Only models with tool calling capabilities can be used with mcp-use. Make sure your chosen model supports function calling or tool use.
Optional Dependencies
Sandbox Execution (E2B)
To use sandboxed execution for running MCP servers in isolated environments:Search Functionality
For enhanced search capabilities:All Optional Dependencies
To install everything:Environment Setup
Create a.env file with your API keys:
.env
Requirements
- Python: 3.11 or higher
- Operating System: Linux, macOS, or Windows
- MCP Servers: Access to MCP server implementations (npm-based or Python-based)
Verifying Installation
Verify your installation by running:Installing from Source
For development or to use the latest features:Next Steps
Quickstart
Get started with your first MCP agent
MCP Agent
Learn about building AI agents with MCP tools