MCP Client-Server Python
by sofianhw
This project demonstrates a simple client-server implementation using the Model Context Protocol (MCP). It allows LLMs to interact with external tools and resources in a standardized way.
Last updated: N/A
What is MCP Client-Server Python?
This is a Python-based client-server example that utilizes the Model Context Protocol (MCP) to enable communication between a client and a server, allowing LLMs to interact with external tools and resources.
How to use MCP Client-Server Python?
- Set up environment variables (OPENAI_API_KEY, MCP_SSE_URL). 2. Start the server using
uv run server.py --host 0.0.0.0 --port 8080. 3. Run the client in another terminal usinguv run client.py. 4. Interact with the client by typing queries, and typequitto exit.
Key features of MCP Client-Server Python
MCP Server exposing tools and resources via SSE
MCP Client connecting to the server and listing available tools
OpenAI Integration for processing user queries and calling server tools
Simple example demonstrating basic MCP functionality
Use cases of MCP Client-Server Python
Demonstrating MCP usage
Building AI agents that can interact with external tools
Creating LLM-powered applications that require access to external resources
Experimenting with different tool integrations for LLMs
FAQ from MCP Client-Server Python
What is MCP?
What is MCP?
MCP (Model Context Protocol) is an open protocol introduced by Anthropic to enable large language models (LLMs) to interact with external tools, APIs, and resources in a standardized, extensible way.
What are the requirements for running this project?
What are the requirements for running this project?
Python 3.12+, MCP Python SDK, OpenAI Python SDK, Uvicorn, python-dotenv, and uv.
How do I install the dependencies?
How do I install the dependencies?
Use uv sync to install all dependencies specified in uv.lock.
How do I start the server?
How do I start the server?
Run uv run server.py --host 0.0.0.0 --port 8080.
How do I run the client?
How do I run the client?
Run uv run client.py in another terminal after starting the server.