AppointmentAgent LiveKit
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., "@AppointmentAgent LiveKitFind next available appointment for John Doe with Dr. Smith."
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.
AppointmentAgent LiveKit
A standalone MCP (Model Context Protocol) server that exposes tools for patient management, appointments, insurance, encounters, and task management against a configurable EHR platform's REST APIs. Designed to be plugged into an LLM-based voice/chat agent (e.g. a LiveKit agent) so it can search patients, book or cancel appointments, verify insurance, and more, entirely through natural language.
Features
29 MCP tools covering patients, insurance, appointments, encounters, tasks, and reference-data lookups (providers, locations, visit reasons, state codes).
Works over stdio (for local MCP clients) or SSE (for HTTP/Docker deployments).
Every tool call is optionally logged to disk for auditing/debugging.
All API base URLs and credentials are supplied via environment variables — nothing is hardcoded.
Related MCP server: FHIR MCP Server
Getting Started
1. Install dependencies
python -m venv .venv
source .venv/bin/activate # or .venv\Scripts\activate on Windows
pip install -r requirements.txt2. Configure environment variables
cp .env.example .envFill in .env with your own EHR platform's base URLs and API credentials. See
.env.example for the full list of required variables.
3. Run the server
# stdio transport (for Claude Desktop / local MCP clients)
python server.py
# SSE transport over HTTP, default port 8000
python server.py --sse
# SSE transport on a custom port
python server.py --sse 30004. Run with Docker
docker compose up --buildProject Structure
.
├── server.py # MCP server + all tool definitions
├── requirements.txt # Python dependencies
├── Dockerfile # Container build
├── docker-compose.yml # Local container orchestration
├── .env.example # Environment variable template (no real secrets)
└── .gitignoreSecurity Notes
Never commit a real
.envfile — it is already excluded via.gitignore.tool_logs/may contain patient data (PHI/PII) from live calls; it is gitignored and should never be committed or shared.Rotate any credentials before reusing this server against a production system.
License
MIT — see LICENSE.
This server cannot be deployed
Maintenance
Related MCP Connectors
Read and write patients, facilities, medical documents, and consolidated FHIR records in Metriport.
Hosted MCP server for the Healthie EHR & telehealth API: patients, appointments, charting, tasks.
Privacy-preserving synthetic health data generation. FHIR R4/R5 compliant.
Hosted MCP server for Cliniko — patients, appointments, availability, and invoices for AI agents.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables LLM-based agents to interact with FHIR healthcare data through natural language prompts, providing full CRUD operations on FHIR resources, document processing, and semantic search capabilities.1399MIT
- AlicenseNot gradedqualityNot gradedmaintenanceEnables seamless integration with FHIR APIs for healthcare applications, allowing users to search, retrieve, create, update, and analyze clinical information through natural language interactions. Supports SMART-on-FHIR authentication and works with various healthcare systems like EPIC and HAPI FHIR servers.Apache 2.0
- FlicenseAqualityDmaintenanceProvides read/write access to any FHIR-compliant healthcare API with built-in validation, supporting resource management, search operations, and granular permissions through natural language.51-
- AlicenseNot gradedqualityCmaintenanceEnables Claude and other AI assistants to trigger HIPAA-compliant patient task management workflows through natural language.1MIT