gabrielpopa/mcp-server
3.1
If you are the rightful owner of mcp-server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to dayong@mcphub.com.
The Model Context Protocol (MCP) server is designed to facilitate communication between machine learning models and various client applications, providing a structured and efficient way to handle model requests and responses.
Local Server MCP
This project provides a local server for MCP (Modular Communication Protocol) using Python.
Getting Started
To run the server with HTTP transport:
export MCP_TRANSPORT=http
export HOST=0.0.0.0
export PORT=3000
python server.py
Internally, this will call:
uvicorn.run(mcp.streamable_http_app(), host=HOST, port=PORT)
To run the server in stdio mode:
python server.py
Features
- Supports HTTP and stdio transport modes
- Configurable host and port
- Easy to run and extend
Requirements
- Python 3.7+
- Uvicorn
- Any other dependencies listed in
requirements.txt
License
See LICENSE for details.