https://github.com/nervo84/mcp-agent
Implementation of an MCP (Model Context Protocol) architecture featuring an MCP client and an MCP server. The project enables structured communication between distributed systems, supporting asynchronous interactions and efficient message handling
https://github.com/nervo84/mcp-agent
Last synced: 2 months ago
JSON representation
Implementation of an MCP (Model Context Protocol) architecture featuring an MCP client and an MCP server. The project enables structured communication between distributed systems, supporting asynchronous interactions and efficient message handling
- Host: GitHub
- URL: https://github.com/nervo84/mcp-agent
- Owner: nervo84
- Created: 2025-04-27T17:08:24.000Z (6 months ago)
- Default Branch: develop
- Last Pushed: 2025-04-28T08:42:33.000Z (6 months ago)
- Last Synced: 2025-04-28T09:33:10.130Z (6 months ago)
- Language: Python
- Size: 64.5 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesome-mcp-servers - **mcp-agent** - MCP Agent is optimized using the ReWOO pattern, enabling even LLMs with fewer parameters to efficiently utilize MCP Server with minimal token consumption. `python` `mcp` `server` `llm` `pip install git+https://github.com/nervo84/mcp-agent` (🤖 AI/ML)
- awesome-mcp-servers - **mcp-agent** - Implementation of an MCP (Model Context Protocol) architecture featuring an MCP client and an MCP server. The project enables structured communication between distributed systems, supporting asynchronous interactions and efficient message handling `python` `mcp` `server` `pip install git+https://github.com/nervo84/mcp-agent` (AI/ML)
README
# MCP Agent
An MCP (Model Context Protocol) server and client using FastMCP and LangChain.
You can watch the video on how it was built on my [YouTube](https://youtu.be/3K39NJbp2IA).
Follow me for updates and future projects:
👉 [LinkedIn](https://www.linkedin.com/in/salvatore-postiglione-927179aa/)
👉 [X (Twitter)](https://x.com/postiglionesax)
# Pre-requisites
Install the dependencies with poetry:
```bash
poetry install
```
Generate an OpenAI API key and set the OPENAI_API_KEY environment variable:
```bash
export OPENAI_API_KEY=...
```
(On Windows, use set instead of export)
# Run
Run the application:
```bash
poetry run mcp_client.py
```