Model Context Protocol (MCP) Server

created by

AdamPippert14 hours ago

an MCP server for the services I like to use with AI agents, which you should probably fork and modify for your own use. No PRs accepted, this is just for me. Not private because you or a bot might get something out of what you see here.

Information

Model Context Protocol (MCP) Server

A modular server that implements the Model Context Protocol standard, providing tools for GitHub, GitLab, Google Maps, Memory storage, and Puppeteer web automation.

Architecture

The MCP server is built with a modular architecture, where each tool is implemented as a separate module. The server provides a unified gateway that routes requests to the appropriate tool.

MCP Server Architecture

Features

MCP Gateway: A unified endpoint for all tool requests following the MCP standard
MCP Manifest: An endpoint that describes all available tools and their capabilities
Direct Tool Access: Each tool can be accessed directly via its own API endpoints
Modular Design: Easy to add or remove tools as needed

Included Tools

GitHub Tool: Interact with GitHub repositories, issues, and search
GitLab Tool: Interact with GitLab projects, issues, and pipelines
Google Maps Tool: Geocoding, directions, and places search
Memory Tool: Store and retrieve data persistently
Puppeteer Tool: Take screenshots, generate PDFs, and extract content from websites

Getting Started

Prerequisites

Python 3.8 or higher
Node.js 14 or higher
A Red Hat-based Linux distribution (RHEL, CentOS, Fedora) or any Linux/macOS system

Installation

Clone this repository:

git clone https://github.com/yourusername/mcp-server.git
cd mcp-server

Install Python dependencies:
```
pip install -r requirements.txt
```
Install Node.js dependencies:
```
npm install
```

Create a .env file with your configuration:

SECRET_KEY=your-secret-key
DEBUG=False

# GitHub configuration
GITHUB_TOKEN=your-github-token

# GitLab configuration
GITLAB_TOKEN=your-gitlab-token

# Google Maps configuration
GMAPS_API_KEY=your-google-maps-api-key

# Memory configuration
MEMORY_DB_URI=sqlite:///memory.db

# Puppeteer configuration
PUPPETEER_HEADLESS=true
CHROME_PATH=/usr/bin/chromium-browser

Start the server:
```
python app.py
```

Containerized Deployment

You can run the server using either Docker or Podman (Red Hat's container engine).

Docker Deployment

If you already have Docker and docker-compose installed:

Build the Docker image:
```
docker build -t mcp-server .
```

Run the container:

docker run -p 5000:5000 --env-file .env mcp-server

Alternatively, use docker-compose:

Create a docker-compose.yml file:

version: '3'
services:
  mcp-server:
    build: .
    ports:
      - "5000:5000"
    volumes:
      - ./data:/app/data
    env_file:
      - .env
    restart: unless-stopped

Then run:

docker-compose up -d

Podman Deployment

For Red Hat based systems (RHEL, CentOS, Fedora) using Podman:

Build the container image:
```
podman build -t mcp-server .
```

Run the container:

podman run -p 5000:5000 --env-file .env mcp-server

If you need persistent storage:

mkdir -p ./data
podman run -p 5000:5000 --env-file .env -v ./data:/app/data:Z mcp-server

Note: The :Z suffix is important for SELinux-enabled systems.

Using Podman Compose (if installed):

# Install podman-compose if needed
pip install podman-compose

# Use the same docker-compose.yml file as above
podman-compose up -d

Using the MCP Server

MCP Gateway

The MCP Gateway is the main endpoint for accessing all tools using the MCP standard.

Endpoint: POST /mcp/gateway

Request format:

{
  "tool": "github",
  "action": "listRepos",
  "parameters": {
    "username": "octocat"
  }
}

Response format:

{
  "tool": "github",
  "action": "listRepos",
  "status": "success",
  "result": [
    {
      "id": 1296269,
      "name": "Hello-World",
      "full_name": "octocat/Hello-World",
      "owner": {
        "login": "octocat",
        "id": 1
      },
      ...
    }
  ]
}

MCP Manifest

The MCP Manifest describes all available tools and their capabilities.

Endpoint: GET /mcp/manifest

Response format:

{
  "manifestVersion": "1.0",
  "tools": {
    "github": {
      "actions": {
        "listRepos": {
          "description": "List repositories for a user or organization",
          "parameters": {
            "username": {
              "type": "string",
              "description": "GitHub username or organization name"
            }
          },
          "returns": {
            "type": "array",
            "description": "List of repository objects"
          }
        },
        ...
      }
    },
    ...
  }
}