Installation

Prerequisites:

Install mcp-use

pip install mcp-use

uv add mcp-use

poetry add mcp-use

This gives you access to everything: MCPAgent, MCPClient, and MCPServer.

If you’re building agents, install your preferred LLM provider:

pip install langchain-openai

pip install langchain-anthropic

pip install langchain-google-genai

pip install langchain-groq

Tool Calling Required: Only models with tool calling capabilities can be used with mcp-use agents.

Create a .env file in your project root:

OPENAI_API_KEY=sk-...
ANTHROPIC_API_KEY=sk-ant-...
GOOGLE_API_KEY=AI...
GROQ_API_KEY=gsk_...

Load them in your scripts:

from dotenv import load_dotenv
load_dotenv()

Install from source for the latest features or to contribute:

git clone https://github.com/mcp-use/mcp-use.git
cd mcp-use/libraries/python
pip install -e .

git clone https://github.com/mcp-use/mcp-use.git
cd mcp-use/libraries/python
pip install -e ".[dev]"

Build AI Agents with tool calling capabilities through MCP connections

A full featured MCP Client implementation for Python

The MCP Server framework implementation for Python

Need Help? Join our Discord or Github communities.