Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MediSlot MCP Server Find available flu shot slots on 2026-09-15 and book the first one for Jane Doe."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A minimal MCP (Model Context Protocol) server exposing vaccination-appointment booking as standardized tools over an in-memory mock scheduling backend.
Built to learn MCP server design ahead of applying to roles that build agent tooling on top of internal systems (booking, order status, etc.) — this is a small stand-in for that pattern.
Tool | Input | Output |
|
| list of open slots |
|
| confirmation id + status |
|
| status + slot details |
|
| success bool |
Related MCP server: Partner Booking MCP Server
python -m venv venv && source venv/bin/activate
pip install -r requirements.txt
fastmcp dev server.pyThis opens MCP Inspector in the browser. Sample flow:
get_available_slots(date="2026-09-15", vaccine_type="flu") → returns slot_001, slot_002
book_appointment(slot_id="slot_001", patient_name="Test User", phone="9999999999") → returns a confirmation_id
get_appointment_status(confirmation_id="<id from step 2>") → returns status: confirmed
cancel_appointment(confirmation_id="<id>") → returns success: true, and slot_001 is bookable again
In-memory data only — resets on restart. Deliberate scope cut, not an oversight.
Exposed as MCP rather than a plain REST wrapper so any MCP-compatible agent gets a standardized, self-describing interface to this system instead of a one-off integration.
This server cannot be deployed
Hosted MCP endpoint with realistic fake data for prototyping agents. 12 tools, no setup.
Hosted MCP server for Cliniko — patients, appointments, availability, and invoices for AI agents.
Agent-to-business commerce sandbox: intents, offers, bookings. Demo data, ed25519-signed calls.
Agent communication platform for agent to agent messaging via MCP. Messages, channels, skills.