​
What is mcp_use?

mcp_use is an open source library that enables developers to connect any Language Learning Model (LLM) to any MCP server, allowing the creation of custom agents with tool access without relying on closed-source or application-specific clients.

​
Key Features

Open Source

Connect any LLM to any MCP server without vendor lock-in

Flexible Configuration

Support for any MCP server through a simple configuration system

Easy Setup

Simple JSON-based configuration for MCP server integration

Universal LLM Support

Compatible with any LangChain-supported LLM provider

HTTP Connection

Connect to MCP servers running on specific HTTP ports for web-based integrations

Dynamic Server Selection

Agents can dynamically choose the most appropriate MCP server for the task.

​
Getting Started

Installation

Install mcp_use and set up your environment

Configuration

Learn how to configure mcp_use with your MCP server

​
Streaming Agent Output

MCP-Use supports asynchronous streaming of agent output using the astream method. This allows you to receive incremental results, tool actions, and intermediate steps as they are generated by the agent.

​
How to use

Call agent.astream(query) and iterate over the results asynchronously:

async for chunk in agent.astream("your query here"):
    print(chunk["messages"], end="", flush=True)

Each chunk is a dictionary containing keys such as actions, steps, messages, and (on the last chunk) output. This enables real-time feedback and progress reporting in your applications.

See the README for more details and usage patterns.