Model Context Protocol (MCP) Server

Name: Model Context Protocol (MCP) Server
Author: AdamPippert

@AdamPippert

Model Context Protocol (MCP) Server について

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.

基本情報

カテゴリ

その他

ライセンス

Apache-2.0

ランタイム

python

トランスポート

stdio

公開者

AdamPippert

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "multi-service-mcp-server": {
      "command": "python",
      "args": [
        "app.py"
      ]
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Model Context Protocol (MCP) Server?

Model Context Protocol (MCP) Server is a modular, container‑ready server that implements the Model Context Protocol standard. It provides a unified gateway and direct access to tools for GitHub, GitLab, Google Maps, Memory (persistent key‑value store), and Puppeteer web automation. Note: This project is no longer being maintained.

How to use Model Context Protocol (MCP) Server?

Install Python 3.8+ and Node.js 14+, clone the repository, install dependencies (pip install -r requirements.txt, npm install), configure a .env file with secrets and API keys, then run python app.py. The server listens on port 5000 by default. Access the MCP Gateway at POST /mcp/gateway or reach individual tools via /tool/<toolname>/....

Key features of Model Context Protocol (MCP) Server

Unified MCP Gateway endpoint for all tool requests
MCP Manifest endpoint describing available tools and capabilities
Direct per‑tool API endpoints (GitHub, GitLab, Google Maps, Memory, Puppeteer)
Modular architecture for adding or removing tools
Containerized deployment with Docker or Podman (including SELinux support)
Persistent memory storage via SQLite (configurable)

Use cases of Model Context Protocol (MCP) Server

Aggregate GitHub and GitLab repository, issue, and pipeline operations in one server
Perform geocoding, directions, and places lookups from Google Maps
Store and retrieve temporary data across AI sessions using the Memory tool
Automate web tasks like screenshots, PDFs, and content extraction via Puppeteer
Provide a single MCP‑compliant entry point for multiple backend services

FAQ from Model Context Protocol (MCP) Server

What does the server do?

It implements the Model Context Protocol to offer a unified gateway for tools that interact with GitHub, GitLab, Google Maps, a persistent memory store, and Puppeteer web automation.

What are the prerequisites?

Python 3.8+, Node.js 14+, and a Red Hat–based Linux distribution, other Linux, or macOS. Docker or Podman are needed for containerized deployment.

How do I configure API keys?

Create a .env file with variables such as GITHUB_TOKEN, GITLAB_TOKEN, GMAPS_API_KEY, and others as documented in the README.

Is this project still maintained?

No. The README clearly states the project is no longer being maintained because the author prefers individual containerized servers over a monolithic routing server.

What transport and authentication does the server use?

The server uses HTTP (Flask web framework) and runs on port 5000. Authentication is handled via secret keys and API tokens configured in the .env file.