brest-mcp-server

brest-mcp-server

0
monitoring

Brest MCP Server is a Model Context Protocol (MCP) server aimed at providing reliable management and deployment of MCP services. It includes an MCP inspector for easy debugging and monitoring, making it user-friendly and robust for MCP-based interactions.

Brest MCP Server

Table of Contents

Description

Brest MCP Server is a server implementation of the Model Context Protocol (MCP) for the Brest region. It provides a robust infrastructure for managing MCP-based interactions and includes an MCP inspector for debugging and monitoring.

The goal of this project is to facilitate the deployment and management of MCP services with a focus on simplicity and reliability.

Technologies

  • Language: Python 3.12.3 or compatible
  • Dependency Management: uv
  • Inspector: MCP Inspector via Node.js (npx)
  • Environment: Virtual environment managed by uv
  • Inspector: MCP Inspector via Node.js (npx)
  • Node.js : Pour l'inspecteur MCP

Installation

To install and configure Brest MCP Server locally, follow these steps:

  1. Install uv (if not already installed):

    • On Linux/macOS: 
      curl -LsSf https://astral.sh/uv/install.sh | sh
    • On Windows: 
      powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

  2. Clone the repository:

    git clone https://github.com/Nijal-AI/Brest-mcp-server.git
cd Brest-mcp-server

  3. Create and activate the virtual environment:

    uv venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

  4. Install the dependencies:

    uv sync

Usage

To run the server locally, proceed as follows:

  1. Ensure the virtual environment is activated:

    source .venv/bin/activate  # On Windows: .venv\Scripts\activate

  2. Start the server with the MCP Inspector:

    npx @modelcontextprotocol/inspector uv run brest-mcp

  3. Access the MCP Inspector in your browser:

    • Proxy: http://localhost:3000
    • Web interface: http://localhost:5173

Example output:

Starting MCP inspector...
Proxy server listening on port 3000
šŸ” MCP Inspector is up and running at http://localhost:5173 šŸš€

Tools

If you want to discut with an AI agent using the Brest MCP Server, you can use the client provided in the tools directory :

uv run python tools/client.py src/server.py

Development

For developers wishing to contribute or work on advanced features, follow these additional steps:

  1. Ensure the virtual environment is set up and dependencies are installed:

    uv venv
uv sync

  2. Use the MCP Inspector to debug and monitor the server:

    npx @modelcontextprotocol/inspector uv run brest-mcp

  3. Refer to the pyproject.toml file for details on dependencies and configurations.

Contributing

Contributions are welcome! To propose changes, follow the file.

License

This project is licensed under the MIT License. See the file for details.