19 Free & Open-Source MCP Servers to Power Your AI Healthcare Applications

amy 09/12/2025

What is an MCP Server?

An MCP Server is a specialized application that implements the Model Context Protocol (MCP), a standardized framework allowing AI assistants (like Claude or Goose) to securely and reliably access external data sources through well-defined tools.

Instead of relying on hallucinations or outdated web searches, an AI can make precise, context-aware requests to a server, such as “Find all Class I recalls for insulin in 2023”, and receive structured, accurate results.

Why MCP is Important (in General & for Healthcare)

In healthcare and medicine, where accuracy and safety are paramount, MCP is revolutionary. It enables AI-powered medical apps to:

  • Access Real Data: Pull up-to-date drug safety info, clinical trial results, and patient vitals directly from authoritative sources like the FDA, WHO, PubMed, and EHRs.
  • Reduce Risk: Prevent dangerous errors by grounding responses in verified data, not guesswork.
  • Accelerate Research: Let researchers quickly find relevant studies, analyze trends, and generate hypotheses.
  • Personalize Care: Enable AI assistants to understand a patient’s full history (medications, allergies, conditions) and provide tailored insights.
  • Build Trust: Offer transparent, auditable interactions with reliable sources, crucial for clinical adoption.

By standardizing access to medical knowledge, MCP servers are laying the foundation for a new generation of safe, intelligent, and impactful healthcare applications.

An MCP Server is crucial for healthcare because it acts as a secure, standardized bridge between powerful AI assistants and critical, real-world medical data sources.

This collection highlights a vibrant ecosystem of open-source Model Context Protocol (MCP) servers transforming how AI interacts with critical medical and scientific data.

From querying the FDA, PubMed, and clinical trials to accessing patient records via FHIR and exploring biological pathways, these servers act as intelligent bridges between powerful AI models and trusted real-world information.

And yes, they are all free and open-source.

1- Healthcare MCP Server

  1. https://github.com/Cicatriiz/healthcare-mcp-public

Healthcare MCP Server is a specialized Node.js server that implements the Model Context Protocol (MCP) to provide AI assistants with access to healthcare data and medical information tools. It enables AI models to retrieve accurate, up-to-date medical information from authoritative sources.

This repository provides a single DXT package containing the complete Node.js implementation.

Included features for this Healthcare MCP Server are:

  • FDA Drug Information: Search and retrieve comprehensive drug information from the FDA database (improved response parsing)
  • PubMed Research: Search medical literature from PubMed’s database of scientific articles
  • Health Topics: Access evidence-based health information from Health.gov (updated to API v4)
  • Clinical Trials: Search for ongoing and completed clinical trials (updated API parameters)
  • Medical Terminology: Look up ICD-10 codes and medical terminology definitions
  • medRxiv Search: Search for pre-print articles on medRxiv
  • Medical Calculator: Calculate Body Mass Index (BMI)
  • NCBI Bookshelf Search: Search the NCBI Bookshelf for biomedical books and documents
  • DICOM Metadata Extraction: Extract metadata from a DICOM file
  • Caching: Efficient caching system with connection pooling to reduce API calls and improve performance
  • Usage Tracking: Anonymous usage tracking to monitor API usage
  • Error Handling: Robust error handling and logging
  • Multiple Interfaces: Support for both stdio (for CLI) and HTTP/SSE interfaces
  • API Documentation: Interactive API documentation with Swagger UI
  • Comprehensive Testing: Extensive test suite with Node.js testing and API verification

2- MCPmed

Think of MCPmed as a smart bridge between AI and real-life biology data, like giving your favorite AI assistant a backstage pass to the world’s most important scientific databases.

Features

  • Direct Database Access: LLMs can query and retrieve data from major biological databases without intermediate APIs
  • Standardized Interfaces: Consistent MCP protocol implementation across all database connectors
  • Extensible Architecture: Cookie-cutter templates enable rapid development of new database integrations
  • Scientific Focus: Tailored specifically for bioinformatics and biomedical research applications

3- Medical MCP Server

This is a free and open-source Model Context Protocol (MCP) server that provides comprehensive medical information by querying multiple authoritative medical APIs including FDA, WHO, PubMed, and RxNorm.

Medical MCP Server’s current features:

  • Search for drugs (brand or generic) using the FDA database, get brand name, generic name, manufacturer, route, dosage form, and purpose
  • Get full drug details using NDC, includes warnings, drug interactions, and clinical pharmacology
  • Pull health statistics from WHO Global Health Observatory – life expectancy, mortality rates, and more by country and year
  • Search scientific articles in PubMed, results include title, PMID, journal, and publication date
  • Search academic papers via Google Scholar (using safe web scraping), results include title, authors, abstract, journal, year, citations, and URL
  • Find standardized drug information using RxNorm, get RxCUI codes, synonyms, and term types

4- Intelligent Medical Assistant

This is a free and open-source comprehensive Patient-Centric Medical Intelligence System that combines MCP (Model Context Protocol) server capabilities with an intelligent web interface. This system provides natural language medical queries, patient data analysis, and professional medical insights powered by Gemini AI.

Intelligent Medical Assistant’ Features:

  • Ask natural language questions like “What is Ben’s sleep summary?” using NLP for intuitive medical queries (Conversational Interface)
  • Automatically routes your query to the right patient data source based on context (Automatic Tool Routing)
  • Delivers professional, evidence-based medical responses with clear disclaimers to ensure safety and accuracy (Professional Medical Responses)
  • Manages real patient records stored in CSV format with biometrics and health tracking (Patient Data Management)
  • Tracks comprehensive health data including sleep patterns, vital signs, lab results, and medications over time (Patient Data Management)
  • Analyzes historical trends in health metrics to uncover insights and patterns (Patient Data Management)
  • Supports multiple patient profiles simultaneously (e.g., Ben Smith, Sarah Jones, Mike Wilson) (Patient Data Management)
  • Integrates seamlessly with Kiro IDE and other MCP clients via a dedicated MCP Server (Dual Architecture)
  • Offers a secure, professional web interface with user authentication for clinical use (Dual Architecture)
  • Provides RESTful API access for programmatic integration with external systems (Dual Architecture)
  • Includes detailed health data for Ben Smith (34M): hypertension, type 2 diabetes, 15 days of sleep data (duration, quality, efficiency), vital signs (BP, heart rate, glucose, weight) (Available Patient Data)
  • Includes asthma history and data for Sarah Jones (28F) (Available Patient Data)
  • Includes high cholesterol profile and data for Mike Wilson (45M) (Available Patient Data)

5- Agent Care: An MCP Server for EMRs like Cerner and Epic

This is a Model Context Protocol (MCP) server that provides healthcare tools and prompts for interacting with FHIR data and medical resources on EMRs like Cerner and Epic using Claude Desktop and Goose Desktop.

AgentCare current features include:

  • EMR integrartion using SMART on FHIR APIs
  • Uses OAuth2 to authenticate with EMRs
  • Anthropic Claude Desktop integration
  • Medical research integration (PubMed, Clinical Trials, FDA)
  • Response caching
  • Error handling
  • Null-safe data formatting
  • Comprehensive clinical analysis

6- Medical MCP Server for Google Cloud Healthcare API (FHIR)

This MCP server connects to Google Cloud Healthcare API (FHIR) via a secure SMART on FHIR gateway with Firebase Auth, letting you access patient data safely.

It works with Claude and Goose Desktop to search for patients, pull vitals, check meds and allergies, find research, and more, all in plain English.

It include a rich features set such as:

  • Connects to Google Cloud Healthcare API (FHIR) via a SMART on FHIR gateway secured with Firebase Auth (enhanced security and access control)
  • Works seamlessly with MCP clients like Claude Desktop and Goose Desktop for natural, conversational medical interactions
  • Provides 12 core FHIR tools for accessing real patient data:
    • find_patient – Search for patients by name, DOB, or identifiers
    • get_patient_observations – Retrieve vital signs and observations
    • get_patient_conditions – Get active medical conditions
    • get_patient_medications – List current medications
    • get_patient_encounters – Access clinical encounter history
    • get_patient_allergies – View allergies and intolerances
    • get_patient_procedures – Retrieve past and planned procedures
    • get_patient_careteam – See care team members
    • get_patient_careplans – Access active care plans
    • get_vital_signs – Pull detailed vital sign trends
    • get_lab_results – Fetch lab test results
    • clinical_query – Run custom FHIR queries for advanced data access
  • Integrates with public medical research APIs:
    • search-pubmed – Find relevant scientific articles
    • search-trials – Discover active clinical trials
    • drug-interactions – Check for potential drug-drug interactions
  • Built for privacy and security: uses Firebase Auth for identity management and secure token flow
  • Designed for real-world use in healthcare workflows: supports timeline views, SOAP notes, patient dashboards, and multi-source data integration
  • Includes demo videos (Claude & Goose), screenshots, and full setup guide for quick onboarding
  • Fully compatible with open-source AI agent frameworks like Goose, enabling flexible model choices beyond Anthropic
  • Ideal for developers, clinicians, and researchers building intelligent, secure, and user-friendly health AI tools

Note that: all features are designed for accuracy, safety, and ease of use, bringing powerful FHIR data and medical research into everyday AI conversations.

8- Python Medical MCP Server

This project is a Python-based MCP server that powers medical AI workflows with dual access: direct Model Context Protocol integration and a modern FastAPI HTTP interface. It centralizes clinical logic in medical_core.py, enabling trauma assessments via RESTful endpoints like /api/medical/trauma-assessment.

It is built for developers, it supports PM2 process management, CORS, Pydantic validation, and seamless deployment. Ideal for health tech apps, research, and AI-driven clinical tools.

It comes with a rich features list that can benefit Python developers include it in their own apps easily:

  • Dual Interface: Direct MCP protocol + FastAPI HTTP API for web clients
  • Centralized Logic: Core medical functions in medical_core.py
  • Trauma Assessment Endpoint: POST /api/medical/trauma-assessment with JSON input
  • Status Check: GET /api/status returns server health and active protocols
  • CORS Enabled: Ready for frontend integration (e.g., Bolt.new)
  • Pydantic Validation: Automatic request/response schema checking
  • PM2 Ready: Auto-restart on boot, easy process management
  • Virtual Environment Support: Clean setup with venv and requirements.txt
  • Manual Dev Mode: Run via uvicorn and Python script for testing
  • Extensible Design: Easy to add new tools, APIs, or clinical logic
  • Production-Ready: Built for scalability, security, and real-world use.

9- MCP Simple PubMed

MCP Simple PubMed is a free, open-source MCP server that gives you easy access to PubMed articles using the Entrez API.

Currently, it does the following:

  • Search PubMed database using keywords
  • Access article abstracts
  • Download full text when available (for open access articles available directly on PubMed)

10- OpenFDA MCP Server

A comprehensive Model Context Protocol (MCP) server that provides access to the U.S. Food and Drug Administration’s public datasets through the openFDA API.

This server enables querying of drug adverse events, product labeling, recalls, approvals, shortages, NDC directory information, and medical device regulatory data including 510(k) clearances, classifications, and adverse events.

Features

Drug Tools (6 tools implemented):

  • search_drug_adverse_events: Search FDA Adverse Event Reporting System (FAERS) data
  • search_drug_labels: Search drug product labeling information
  • search_drug_ndc: Query the National Drug Code (NDC) directory
  • search_drug_recalls: Find drug recall enforcement reports
  • search_drugs_fda: Search the Drugs@FDA database for approved products
  • search_drug_shortages: Query current drug shortages

Device Tools (4 tools implemented):

  • search_device_510k: Search FDA 510(k) device clearances
  • search_device_classifications: Search FDA device classifications
  • search_device_adverse_events: Search FDA device adverse events (MDR)
  • search_device_recalls: Search FDA device recall enforcement reports

Other Features:

  • Comprehensive Search: Advanced filtering by drug name, manufacturer, indication, dates, and more
  • Rate Limiting: Built-in awareness of FDA API rate limits (1,000 requests/hour without API key)
  • Error Handling: Robust error handling with meaningful error messages
  • Formatted Results: Clean, structured JSON responses with relevant metadata
  • Optional API Key: Supports FDA API key for higher rate limits (120,000 requests/hour)

11- Biomedical public MCP Servers

This collection gives AI tools easy access to top biomedical resources, like PubMed, clinical trials, drug data, and preprints, all through simple, smart connections. No complex setup needed. Just ask, and the AI pulls accurate, up-to-date info from trusted sources.

It is perfect for researchers, students, and developers who want fast answers without digging through websites. All tools are open and free to use, making science more accessible and collaborative.

Available Servers

Access the PubMed database of biomedical literature.

  • Search PubMed for articles matching a query
  • Retrieve abstracts for specific articles
  • Find related articles based on a PMID
  • Search for articles by a specific author

BioRxiv/MedRxiv MCP Server:

Access preprints from bioRxiv and medRxiv repositories.

  • Get detailed information about preprints by DOI
  • Find published versions of preprints
  • Search for recent preprints
  • Search preprints by date range and category

ClinicalTrials.gov MCP Server

Access information about clinical trials.

  • Search for trials matching specific criteria
  • Get detailed information about specific trials
  • Find trials by medical condition
  • Find trials by location

DrugBank MCP Server

Access drug information from DrugBank.

  • Search for drugs by name
  • Get detailed information about specific drugs
  • Find drugs by indication
  • Find drugs by category
  • Get drug interaction information

OpenTargets MCP Server

Access drug target information from Open Targets.

  • Search for gene targets
  • Get detailed target information
  • Search for diseases
  • Find disease-target associations
  • Search for drugs

12- CharmHealth EHR

CharmHealth MCP Server is a an open-source MCP server for CharmHealth EHR that allows LLMs and MCP clients to interact with patient records, encounters, and practice information.

The server provides 14 comprehensive tools for complete EHR functionality:

  • Encounter Management: Complete SOAP note workflow and clinical findings
  • Patient Search & Records: Advanced patient search with demographics, location, and medical criteria
  • Patient Management: Complete demographic and administrative data handling
  • Medical History: Comprehensive patient clinical overview and history review
  • Drug Management: Unified medications, supplements, and prescribing with safety checks
  • Allergy Management: Critical allergy documentation with safety alerts
  • Diagnosis Management: Problem list and diagnosis tracking
  • Clinical Notes: Quick clinical observations and provider communications
  • Recalls & Follow-ups: Preventive care reminders and appointment scheduling
  • Vital Signs: Complete vital signs recording and trend monitoring
  • File Management: Patient photos, documents, and PHR invitations
  • Laboratory Management: Lab results tracking and detailed reporting
  • Practice Setup: Facilities, providers, and vital sign templates
  • Appointment Management: Complete appointment lifecycle with scheduling and rescheduling

13- Cortellis Drug Database

The Cortellis Drug Database MCP server brings powerful drug research data directly into Cursor. Easily set up with your credentials, it enables seamless access to comprehensive pharmaceutical insights. Perfect for developers and researchers, it enhances AI workflows with reliable, real-time drug information. It is ideal for innovation in healthcare and life sciences.

14- PopHIVE MCP Server

PopHIVE (Population Health Information Visual Explorer) is Yale’s comprehensive platform that aggregates near real-time public health data from authoritative sources including CDC surveillance systems, Epic Cosmos EHR networks, and Google Health Trends.

It’s an invaluable resource for epidemiologists, researchers, and public health professionals.

PopHIVE MCP Server’s features include:

  • 🩺 Real-time Health Data Hub: Aggregates near real-time data from CDC, Epic, Google, and more
  • 📊 12+ Datasets: Immunizations, respiratory viruses, hospital capacity, overdose deaths, youth mental health ED visits, chronic disease stats, wastewater surveillance, and more
  • 🔍 Smart Search: Find data by condition, state, or keyword with search_health_data
  • 📉 Compare States: Analyze metrics across states with built-in stats and visual trends
  • ⏱️ Fast & Efficient: Parallel batch fetching + incremental updates = lightning-fast load times
  • 🧩 Filter Any Way: Narrow down data by state, date range, demographics, and conditions
  • 📈 Trend Analysis: Time-series tools for spotting patterns in outbreaks, vaccination gaps, or chronic disease trends
  • 🔄 Auto-Updates: Scrapers only pull new data — no redundant downloads
  • 🛠️ Robust Parsing: Handles messy dates and formats across all sources
  • 💡 Smart Prompts: One-click analysis: “Find immunization gaps”, “Detect respiratory surges”, “Track chronic disease trends”
  • 🌐 MCP Ready: Works seamlessly with Claude Desktop, Goose, and other AI agents

15- BioMCP: Biomedical Model Context Protocol

BioMCP is an open source (MIT License) toolkit that empowers AI assistants and agents with specialized biomedical knowledge. Built following the Model Context Protocol (MCP), it connects AI systems to authoritative biomedical data sources, enabling them to answer questions about clinical trials, scientific literature, and genomic variants with precision and depth.

It lets researchers ask natural language questions to find clinical trials, scientific papers, and genetic variants, no complex queries needed. By acting as a smart bridge between AI and trusted databases, BioMCP simplifies research workflows, supports evidence-based decisions, and turns general knowledge into precise, up-to-date insights for science and medicine.

It comes with a search tool, domain-based search and filter tool, fetch tool, trail tool, variant tools, NCI-specific tools, and Gene, disease & drug tools.

BioMCP integrates with multiple biomedical data sources:

1- Literature Sources

  • PubTator3/PubMed – Peer-reviewed biomedical literature with entity annotations
  • bioRxiv/medRxiv – Preprint servers for biology and health sciences
  • Europe PMC – Open science platform including preprints

2- Clinical & Genomic Sources

  • ClinicalTrials.gov – Clinical trial registry and results database
  • NCI Clinical Trials Search API – National Cancer Institute’s curated cancer trials database
    • Advanced search filters (biomarkers, prior therapies, brain metastases)
    • Organization and intervention databases
    • Disease vocabulary with synonyms
  • BioThings Suite – Comprehensive biomedical data APIs:
    • MyVariant.info – Consolidated genetic variant annotation
    • MyGene.info – Real-time gene annotations and information
    • MyDisease.info – Disease ontology and synonym information
    • MyChem.info – Drug/chemical annotations and properties
  • TCGA/GDC – The Cancer Genome Atlas for cancer variant data
  • 1000 Genomes – Population frequency data via Ensembl
  • cBioPortal – Cancer genomics portal with mutation occurrence data
  • OncoKB – Precision oncology knowledge base for clinical variant interpretation (demo server with BRAF, ROS1, TP53)
    • Therapeutic implications and FDA-approved treatments
    • Oncogenicity and mutation effect annotations
    • Works immediately without authentication

3- Regulatory & Safety Sources

  • OpenFDA – FDA regulatory and safety data:
    • Drug Adverse Events (FAERS) – Post-market drug safety reports
    • Drug Labels (SPL) – Official prescribing information
    • Device Events (MAUDE) – Medical device adverse events, with genomic device filtering

16- Nexonco by Nexgene Research is an MCP server

This is an advanced MCP Server for accessing and analyzing clinical evidence data, with flexible search options to support precision medicine and oncology research.

The tool accepts the following optional parameters:

  • disease_name (str): Filter by disease (e.g., “Lung Non-small Cell Carcinoma”).
  • therapy_name (str): Filter by therapy or drug (e.g., “Cetuximab”).
  • molecular_profile_name (str): Filter by gene or variant (e.g., “EGFR L858R”).
  • phenotype_name (str): Filter by phenotype (e.g., “Chest Pain”).
  • evidence_type (str): Filter by evidence type (e.g., “PREDICTIVE”, “DIAGNOSTIC”).
  • evidence_direction (str): Filter by evidence direction (e.g., “SUPPORTS”).
  • filter_strong_evidence (bool): If True, only includes evidence with a rating > 3 (max 5).

17- Unofficial Reactome MCP Server 🧬

This MCP server unlocks Reactome’s biological pathways and systems biology data for AI tools. Perfect for researchers, it lets you explore complex cellular processes with simple questions.

It is powered by Augmented Nature, it turns intricate science into clear, actionable insights, making discovery faster, smarter, and more collaborative.

Verified Features:

  • Pathway Search – Search biological pathways by name, process, keywords
  • Pathway Details – Comprehensive pathway information and components
  • Gene-to-Pathways – Find pathways containing specific genes/proteins
  • Disease Pathways – Disease-associated biological mechanisms
  • Pathway Hierarchy – Parent/child relationships and pathway structure
  • Pathway Participants – All molecules participating in pathways
  • Biochemical Reactions – Detailed reaction information
  • Protein Interactions – Molecular interactions within pathways

18- Pubmed-mcp-server

This MCP server gives AI agents powerful, reliable access to PubMed’s vast medical literature. Search articles by topic, fetch full details by PMID, find related studies, generate research plans, and create visual charts from data.

It is built for researchers and developers, it turns complex queries into actionable insights, all while ensuring accuracy and up-to-date results. Perfect for accelerating biomedical discovery and supporting evidence-based decision-making in science and healthcare.

Key Features:

  • Free-text search across all article fields (title, abstract, author, journal).
  • Filter by publication date range and specific publication types (e.g., “Review”, “Clinical Trial”).
  • Sort results by relevance, publication date, author, or journal name.
  • Optionally fetch brief summaries for top results in the same call.

Example Use Cases:

  • “Find recent review articles on CRISPR gene editing.”
  • “Show me all publications by Dr. Anthony Fauci in 2023.”
  • “List the latest articles on neuroinflammation in the journal ‘Nature’.”

19- OLS MCP Server

This MCP server makes it easy for AI to work with complex medical and biological ontologies, no more guesswork or hallucinations. It connects to the Ontology Lookup Service (OLS) so you can search terms, find the right ontology, and get accurate, up-to-date info in plain language.

The server is perfect for researchers, developers, and clinicians who want reliable answers fast. Works seamlessly with tools like Claude Desktop, turning confusing codes into clear, helpful insights. Science made simpler, one term at a time.

The OLS MCP Server provides the following tools:

  • Search Terms: Search for terms across ontologies with flexible filtering
  • Search Ontologies: Discover available ontologies and their metadata
  • Get Ontology Information: Retrieve detailed information about specific ontologies
  • Get Term Information: Get comprehensive details about specific terms
  • Get Term Children: Find direct child terms in ontological hierarchies
  • Get Term Ancestors: Retrieve parent terms and ancestors
  • Find Similar Terms: Discover semantically similar terms using LLM embeddings

The server works with any ontology available through the EBI Ontology Lookup Service, including:

  • GO (Gene Ontology)
  • EFO (Experimental Factor Ontology)
  • HP (Human Phenotype Ontology)
  • MONDO (Monarch Disease Ontology)
  • ChEBI (Chemical Entities of Biological Interest)
  • UBERON (Uber-anatomy ontology)
  • And many more…

Further Readings

Related articles