MCP-hub-personal

MCP Server personalizado que integra herramientas de uso cotidiano (Gmail, Google Calendar, Drive, VSCode y GitHub) con clientes compatibles VSCode Copilot, Codex y Claude for Desktop.

Installation

Run this command in your terminal to add the MCP server to Claude Code.

Run in terminal:

View docs

Command

claude mcp add --transport stdio ricardouchub-mcp-hub-personal uvx run mcp dev mcp_hub/server.py \
  --env GITHUB_TOKEN="GITHUB_TOKEN" \
  --env GOOGLE_SCOPES="https://www.googleapis.com/auth/gmail.readonly https://www.googleapis.com/auth/gmail.modify https://www.googleapis.com/auth/gmail.send https://www.googleapis.com/auth/calendar https://www.googleapis.com/auth/drive https://www.googleapis.com/auth/drive.metadata.readonly" \
  --env GOOGLE_TOKEN_PATH="data/token.google.json" \
  --env GOOGLE_CREDENTIALS_PATH="secrets/credentials.google.json"

How to use

MCP Hub Personal is a multi-service local hub built with FastMCP to orchestrate Gmail, Google Calendar, Drive, VSCode local actions, and GitHub interactions through compatible clients. It exposes a set of tools (endpoints) such as gmail_list_unread, gmail_search_messages, calendar_create_event, drive_search, github_list_repos, vscode_open, and more. You can connect clients like Codex, Claude Desk, or Copilot by pointing them at the MCP server and feeding the proper environment variables (credentials and tokens). Use the built-in inspector (via uv run mcp dev) during development to test tool calls and validate responses before running in production.

How to install

Prerequisites:\n- Python 3.10+\n- uv (Python environment tooling)\n- Access to Google OAuth2 credentials (credentials.google.json) and a GitHub token with repo scope.\n\n1) Clone the repository:\nbash\ngit clone https://github.com/Ricardouchub/mcp-hub-ricardo.git\ncd mcp-hub-ricardo\n\n2) Install and sync the Python environment with uv:\nbash\nuv sync\nuv pip install -e .\n\n3) Prepare credentials and tokens:\n- Place Google OAuth credentials at secrets/credentials.google.json.\n- Obtain an initial Google token and save it to data/token.google.json.\n- Ensure you have a GitHub token with the required scopes and set it in your environment or configuration as GITHUB_TOKEN.\n4) Run the Inspector MCP (development):\nbash\nuv run mcp dev mcp_hub/server.py\n\n5) For production STDIO mode (no inspector):\nbash\nuv run mcp run stdio mcp_hub/server.py\n

Additional notes

Tips and caveats:\n- The server relies on Google OAuth2 credentials and a persisted token; keep credentials.google.json and token.google.json secure. If you modify scopes, you may need to re-authenticate and regenerate the token.\n- The GITHUB_TOKEN should be kept secret and provided by your CI or local environment.\n- The integration notes assume a project root structure similar to the repository; adjust paths in the environment variables if you relocate files.\n- VSCode/Claude/Codex integrations expect the MCP server to be reachable via the configured transport (stdio) and will read the same environment variables for credentials.\n- If you encounter issues, start with the inspector (dev mode) to test individual tools like calendar_upcoming or gmail_list_unread and verify OAuth scopes.\n- The README indicates optional Inspector support via Node.js tooling; the core MCP server itself runs under Python uv/uvx in this setup.

Related MCP Servers

skillport

327

Bring Agent Skills to Any AI Agent and Coding Agent — via CLI or MCP. Manage once, serve anywhere.

pfsense

pfSense MCP Server enables security administrators to manage their pfSense firewalls using natural language through AI assistants like Claude Desktop. Simply ask "Show me blocked IPs" or "Run a PCI compliance check" instead of navigating complex interfaces. Supports REST/XML-RPC/SSH connections, and includes built-in complian

mcp-kubernetes

A Model Context Protocol (MCP) server that enables AI assistants to interact with Kubernetes clusters. It serves as a bridge between AI tools (like Claude, Cursor, and GitHub Copilot) and Kubernetes, translating natural language requests into Kubernetes operations and returning the results in a format the AI tools can understand.

skill-to

Convert AI Skills (Claude Skills format) to MCP server resources - Part of BioContextAI

fastmcp-gsuite

MCP server for Gmail, Google Calendar, and Google Drive integration using fastmcp. Supports multiple accounts, email management, calendar events, and file operations.

mycobot

myCobot MCP(Model Context Protocol) server