Skip to main content
Glama
majincleaning-ops

majincleaning-ops

MajinCleaningSolutions Ops MCP Server

An MCP server that connects an AI assistant (Claude Desktop, Claude Code, or any other MCP-compatible client) directly to the real, live Supabase database behind MajinCleaningSolutions — my production booking app for a real cleaning business.

Instead of logging into the site's /admin dashboard to check the schedule, you can just ask: "What's my availability next Tuesday?" or "Show me pending bookings" — and the assistant answers using real data, live, through this server.

Why this exists

MCP is the emerging standard ("USB-C for AI") for connecting AI models to real tools and data instead of every app writing its own one-off integration. This server is a small, honest example of that pattern applied to a real system I already built and operate — not a toy dataset.

Related MCP server: Supabase MCP Server

Tools it exposes

Tool

What it does

list_services

Returns current services and flat-rate pricing

check_availability

Given a date, returns open vs. taken appointment slots

list_upcoming_bookings

Lists upcoming bookings, optionally filtered by status

update_booking_status

Updates a booking's status, enforcing the same pending → confirmed → completed/cancelled rules the admin dashboard uses

A deliberate security decision

The live site's public booking form uses Supabase's anon key, which — by Row Level Security policy — can submit a booking but can never read anyone else's data back. That's correct for a public website.

This server is different: it runs locally, under my own control, standing in for the business owner using the admin dashboard. So it uses the service role key instead, which can read and update real booking data. That key lives only in a local, gitignored .env file — it's never committed, never shipped to a browser, and this server is never deployed publicly. Same database, two different trust levels depending on who's asking.

Setup

npm install
cp .env.example .env
# fill in SUPABASE_URL and SUPABASE_SERVICE_ROLE_KEY from your Supabase
# project's Settings -> API page
npm run build

Connect it to Claude Desktop

Add this to your Claude Desktop MCP config (claude_desktop_config.json):

{
  "mcpServers": {
    "majincleaning-ops": {
      "command": "node",
      "args": ["/absolute/path/to/majincleaning-ops-mcp/dist/index.js"],
      "env": {
        "SUPABASE_URL": "https://your-project-ref.supabase.co",
        "SUPABASE_SERVICE_ROLE_KEY": "your-service-role-key"
      }
    }
  }
}

Restart Claude Desktop, and the four tools above become available for it to call directly against the real database.

Tech

Node.js + TypeScript, the official @modelcontextprotocol/sdk, and @supabase/supabase-js. Business-hours/slot logic mirrors lib/availability.ts and status-transition rules mirror lib/validation.ts from the main site's repo, so this server enforces the exact same business rules as the production app.

Built on top of WebsiteProject — the full-stack Next.js + Supabase + Vercel app this server connects to.


By: Jahzeel Reyes

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      Not graded
      maintenance
      Enables AI assistants to interact with Supabase databases through standardized CRUD operations including querying, inserting, updating, and deleting records with support for filtering, pagination, and column selection.
      -
    • A
      license
      B
      quality
      B
      maintenance
      Enables AI assistants to access and manage Streamline tasks, notes, tags, and workspaces via a Supabase-powered backend. It supports full CRUD operations, allowing users to search, create, update, and organize their productivity data through natural language.
      17
      MIT