Claude Desktop
Desktop · Freemium · Proprietary
Anthropic's official Claude AI desktop application. Supports MCP servers to extend functionality.
WindowsMacOS
Health & Wellness · Developer Tools
Fhir MCP Server
the-momentum/fhir-mcp-server
FHIR MCP Server is a medical data management server based on the FastMCP framework, providing a complete Model Context Protocol (MCP) implementation that supports interaction between LLM agents and FHIR-compatible backends. It offers standardized interfaces, supports comprehensive CRUD operations on FHIR resources, and enables intelligent document processing and semantic search through a set of tools.
Install
Client configuration
{
"mcpServers": {
"docker-mcp-server": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"--init",
"--name",
"fhir-mcp-server",
"--mount",
"type=bind,source=<your-project-path>/app,target=/root_project/app",
"--mount",
"type=bind,source=<your-project-path>/config/.env,target=/root_project/config/.env",
"-e",
"TRANSPORT_MODE=stdio",
"mcp-server:latest"
]
}
}
}- Author
- @the-momentum
- Category
- Health & Wellness, Developer Tools
- License
- MIT
- Updated
- Oct 6, 2026
About Fhir MCP Server
Model Context Protocol (MCP) Server for Fast Healthcare Interoperability Resources (FHIR)
Features
FastMCP Framework: Built on FastMCP for high-performance MCP server capabilities
FHIR Resource Management: Full CRUD operations for all major FHIR resources
Intelligent Document Processing: AI-powered document ingestion and chunking for multiple formats including TXT, CSV, JSON, and PDF
Semantic Search: Advanced document search using vector embeddings (via Pinecone)
RAG-Ready: Retrieval-Augmented Generation pipeline with context-aware document queries
Secure Authentication: OAuth2 token management for FHIR API integration
LOINC Integration: Standardized medical terminology lookup and validation
Container Ready: Docker support for easy deployment and scaling
Configurable: Extensive.env-based configuration options
Tools (14)
request_patient_resource
Manage patient demographic and administrative information
request_observation_resource
Observation
request_condition_resource
Condition
request_medication_resource
Medication
request_immunization_resource
Immunization
request_encounter_resource
Encounter
request_allergy_intolerance_resource
AllergyIntolerance
request_family_member_history_resource
FamilyMemberHistory
request_generic_resource
Any FHIR Resource
request_document_reference_resource
Manage FHIR DocumentReference resources
add_document_to_pinecone
Ingests documents into the vector database for semantic search
search_pinecone
Performs semantic search across indexed documents using vector embeddings
get_loinc_codes
Retrieves standardized LOINC codes for medical observations and laboratory tests
Security
OAuth2 authentication and proper access control for all operations
Details on this page are taken from the project's README. Open README
Supported clients
Clients mentioned in this server's README:
Related MCP servers
HowToCook-mcp
worryzyy/HowToCook-mcp
An MCP (Model Context Protocol) server based on Anduin2017/HowToCook, allowing AI assistants to recommend recipes, plan meals, and solve the age-old question of "what should I eat today?".
NexOnco (CIViC Precision Oncology)
nexgene-research/nexonco-mcp
search_clinical_evidence: A MCP tool for querying clinical evidence data that returns formatted reports.
Agentcare MCP
Kartha-AI/agentcare-mcp
Agent Care is an MCP-based server for interacting with electronic medical record systems such as Cerner and Epic, providing medical tools and FHIR data access.
DICOM
christianhinge/dicom-mcp
The dicom-mcp server enables AI assistants to query, read, and move data on DICOM servers (PACS, VNA, etc.).
Health Record MCP
jmandel/health-record-mcp
This project acts as a specialized server providing tools for Large Language Models (LLMs) and other AI agents to interact with Electronic Health Records (EHRs). It leverages the SMART on FHIR standard for secure data access and the Model Context Protocol (MCP) to expose the tools.
Strava MCP
r-huijts/strava-mcp
Connect Claude to your Strava account and ask questions in plain English: "How far did I run this month?", "Analyze my last ride", or "Show me my fastest segments.".