majincleaning-ops
Enables AI assistants to query and manage real booking data from MajinCleaningSolutions via Supabase, including checking availability, listing bookings, and updating status.
README
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.
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.
Related
Built on top of WebsiteProject — the full-stack Next.js + Supabase + Vercel app this server connects to.
By: Jahzeel Reyes
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.