Skip to main content
Glama
baala-saravanan

FHIR MCP Server

by baala-saravanan
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

šŸ„ FHIR MCP Server

A FastMCP server that exposes healthcare data from the Public HAPI FHIR R4 Server using the Model Context Protocol (MCP).

This project demonstrates how AI applications can interact with standardized Electronic Health Record (EHR) data through FHIR resources.

Features

  • Search patients by name

  • Retrieve patient demographics

  • Retrieve medical conditions

  • Retrieve observations

  • Retrieve medication requests

  • Async communication using HTTPX

  • Compatible with MCP Inspector

  • Built using FastMCP

Related MCP server: LangCare MCP FHIR Server

Technologies

  • Python 3.11+

  • FastMCP

  • MCP

  • HTTPX

  • FHIR R4

  • Public HAPI FHIR Server

Project Structure

fhir-mcp-server/
ā”‚
ā”œā”€ā”€ server.py
ā”œā”€ā”€ requirements.txt
ā”œā”€ā”€ README.md
ā”œā”€ā”€ LICENSE
ā”œā”€ā”€ .gitignore
ā”‚
ā”œā”€ā”€ screenshots/
ā”‚   ā”œā”€ā”€ home.png
ā”‚   ā”œā”€ā”€ search_patient.png
ā”‚   ā”œā”€ā”€ get_patient.png
ā”‚   ā”œā”€ā”€ get_conditions.png
ā”‚   ā”œā”€ā”€ get_observations.png
ā”‚   ā”œā”€ā”€ get_medications.png
ā”‚   ā””ā”€ā”€ architecture.png
ā”‚
ā””ā”€ā”€ docs/
    ā””ā”€ā”€ architecture.md

Installation

Clone the repository:

git clone https://github.com/baala-saravanan/fhir-mcp-server.git
cd fhir-mcp-server

Create a virtual environment:

python -m venv .venv

Activate the environment:

Windows:

.venv\Scripts\activate

Install dependencies:

pip install -r requirements.txt

Running the Project

Launch the MCP development server:

mcp dev server.py

The MCP Inspector will open automatically in your browser.

Available MCP Tools

Tool

Description

search_patient

Search patients by name

get_patient

Retrieve patient demographics

get_conditions

Retrieve patient conditions

get_observations

Retrieve laboratory results and observations

get_medications

Retrieve medication history

Data Source

Public HAPI FHIR R4 Test Server

https://hapi.fhir.org/baseR4

This server provides synthetic healthcare data for development and testing.

Architecture

The application follows the Model Context Protocol (MCP) architecture.

See:

  • docs/architecture.md

  • screenshots/architecture.png

Screenshots

The project includes screenshots demonstrating the available MCP tools.

  • Home

  • Search Patient

  • Get Patient

  • Get Conditions

  • Get Observations

  • Get Medications

  • Architecture Diagram

Future Improvements

  • Patient Timeline

  • Clinical Summary

  • Laboratory Trend Analysis

  • Medication Intelligence

  • Clinical Decision Support

  • AI-powered Patient Summaries

  • Streamlit Dashboard

  • FastAPI Backend

  • LLM Integration

License

This project is licensed under the MIT License.

See the LICENSE file for details.

Author

Bala Saravanan Muthukumar

  • Data Scientist

  • Biomedical Engineer

  • AI & Healthcare Enthusiast

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • Heavenly Health Protocol

    xbirimensah
    A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI clients to securely access, query, and mutate normalized user-controlled health data (e.g., from Apple Health or Supabase) through a bounded set of MCP tools, with optional OAuth and sandboxed deployment.
    MIT

  • FHIR MCP Server

    Sharma8610
    F
    license
    Not graded
    quality
    A
    maintenance
    Enables LLM-based agents and MCP-compatible clients to query and manipulate clinical data on a FHIR-compliant backend through CRUD resource tools, document ingestion, semantic search, and terminology lookup.
    -

  • FHIR MCP Server

    sarac083
    F
    license
    Not graded
    quality
    A
    maintenance
    Enables LLM-based agents and MCP-compatible clients to query and manipulate FHIR resources through full CRUD tools, with document ingestion, semantic search, LOINC terminology lookup, and OAuth2-authenticated FHIR API integration.
    -