Partner Booking MCP Server
Simulates a third-party appointment booking agent, enabling your AI platform to check availability and book appointments via MCP interoperability.
README
Partner Booking MCP Server (demo external agent)
A tiny, self-contained external MCP server that simulates a third-party vendor's appointment-booking agent. Point your platform's agent at its public URL to demonstrate real-time agent-to-agent interoperability — your agent orchestrating and exchanging tasks/context with an AI capability that is not hosted on your platform.
Transport: Streamable HTTP (stateless), so it deploys to any Node host and is reachable as a normal HTTPS endpoint.
Tools exposed
| Tool | What it does |
|---|---|
check_availability |
Open slots for a service + date |
book_appointment |
Books a slot, returns a confirmation id |
cancel_appointment |
Cancels by confirmation id, frees the slot |
list_appointments |
Lists bookings (optional customer filter) |
Services seeded: haircut, dental-checkup, car-service, consultation.
Dates seeded: 2026-07-27, 2026-07-28, 2026-07-29. (In-memory — resets on restart.)
Run locally
npm install
npm start # -> http://localhost:3000/mcp
Quick smoke test:
curl -X POST http://localhost:3000/mcp \
-H 'Content-Type: application/json' \
-H 'Accept: application/json, text/event-stream' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'
Deploy to a public URL
Render (easiest — render.yaml included):
- Push this folder to a GitHub repo.
- Render → New → Blueprint → pick the repo. It reads
render.yaml. - You get a URL like
https://partner-booking-mcp.onrender.com. Your MCP endpoint ishttps://.../mcp.
Railway / Fly / Cloud Run: same idea — Node app, start command node server.js,
expose $PORT. A Dockerfile is included if the host prefers containers.
Free Render instances sleep when idle. Hit the URL once ~30s before the demo to wake it.
Connect it to your platform (the demo moment)
Register it as a remote MCP server in whatever your platform uses:
- Endpoint / URL:
https://<your-host>/mcp - Transport: Streamable HTTP
- Auth: none (demo). Add a bearer-token check in
server.jsif your platform requires one.
To try it in a generic MCP client, the connection config looks like:
{
"mcpServers": {
"partner-booking": {
"type": "http",
"url": "https://<your-host>/mcp"
}
}
}
Suggested demo script
- User asks your platform's agent: "Book me a haircut next Monday morning."
- Your agent calls
check_availabilityon this external server → shows the slots. - Your agent calls
book_appointment→ returns confirmationBK-XXXXXXXX. - Emphasise: the booking logic + data live in a separate, third-party service — your platform discovered its tools and orchestrated the task live over MCP.
- Optional:
cancel_appointmentto show a two-way, stateful exchange.
Notes for a production-shaped story
- Add auth (bearer/OAuth) at the
/mcproute. - Swap the in-memory store for a real DB/booking API.
- Same pattern maps to any partner capability — this is intentionally minimal so the interoperability is the star, not the business logic.
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.