Open catalog · Healthcare commons · Early access

Machine-Actionable
Catalog for Healthcare

An open, curated registry of open-source healthcare software, AI models, clinical standards, datasets, and MCP servers — structured so humans and agents can both find and use them.

v0.1 early access  — entries are curated and trustworthy; automations and validations are Phase 2

Structured metadata

Every entry is
standards-compliant

Each entry serializes against the right open metadata standard for its type, making the catalog queryable by software, reproducible in research, and ready for downstream portals.

Software CodeMeta 3.0
AI / ML models MLDCAT-AP 3.0
Datasets Croissant
MCP servers server.json
Catalog DCAT-AP
Data products Bitol ODPS
Standards / Specs schema.org + MACH

Taxonomy

7 entry types
across the commons

From clinical software to AI agents — every open healthcare artifact has a home here.

01Software
02AI / ML Models
03Datasets
04MCP Servers
05Data Sources
06Catalogs
07Specs

Catalog entries

Live entries,
growing with every commit

Every entry is a structured JSON-LD file in the repository. This list updates automatically on each push via CI. Contributions welcome via GitHub issues or the form below.

Total entries

53

Entry types

6/7

2626
Category
License
Catalogs

Health-RI Data Catalogue

Dutch national health research data catalogue built on the FAIR Data Point (FDP) specification. Metadata is described using HealthDCAT-AP, t…

↗ site
Catalogs

SPHN Metadata Catalog

Swiss national health research metadata catalog operated by the SIB Swiss Institute of Bioinformatics for the Swiss Personalized Health Netw…

↗ site
Datasets

AgentClinic

Multimodal medical agent benchmark that simulates end-to-end clinical workflows. Presents AI agents with patient-facing dialogue, EHR record…

↗ site↗ repo
Datasets

FHIR-AgentBench

Benchmark for evaluating LLM agent ability to retrieve and answer clinical questions from FHIR-structured EHR data. Contains approximately 3…

↗ site↗ repo
Datasets

MedAgentBench

FHIR-native benchmark for evaluating AI agents on real-world clinical tasks authored by practising physicians. Contains 300 tasks across 10 …

↗ site↗ repo
Datasets

MedCalc-Bench

Benchmark dataset for evaluating LLM ability to perform clinical calculator tasks — a common but under-tested dimension of medical reasoning…

↗ site↗ repo
Datasets

MLOmics Cancer Multi-Omics Benchmark

Standardised multi-omics benchmark dataset covering all 32 TCGA cancer types across four omics modalities: mRNA expression, microRNA, DNA me…

↗ site↗ reposwh
Datasets

NHS England Synthetic Clinical Notes

Synthetic clinical notes dataset generated by NHS England Data Science to support clinical NLP research and model development without exposi…

↗ site
MCP Servers

FHIR MCP Server (WSO2)

Exposes any FHIR R4/R5 server as an MCP server, enabling LLM agents to perform CRUD operations on FHIR resources through natural language vi…

↗ reposwh
MCP Servers

OMCP

Model Context Protocol (MCP) server for the OMOP Common Data Model. Provides a structured, secure interface for LLM agents to query and anal…

↗ site↗ repo
MCP Servers

openEHR Assistant MCP (Cadasto)

MCP server bridging AI assistants with openEHR design-time workflows. Exposes CKM archetype and template search, openEHR terminology concept…

↗ reposwh
MCP Servers

openEHR MCP Server (deak-ai)

MCP server for runtime interaction with EHRbase via openEHR REST APIs. Exposes 11 MCP tools covering template operations, EHR lifecycle mana…

↗ reposwh
MCP Servers

MCP SNOMED CT

Experimental MCP server exposing SNOMED CT concept lookup to LLM agents via any FHIR R4 terminology server. Enables AI agents to resolve cli…

↗ repo
AI / ML Models

GeneAgent

Self-verifying LLM agent for gene-set analysis that autonomously queries domain databases (Gene Ontology, KEGG, NCBI Gene, PubMed) to annota…

↗ site↗ repo
AI / ML Models

nnDetection

Self-configuring framework for 3D volumetric medical object detection, applying the same automated configuration philosophy as nnU-Net to de…

↗ reposwh
AI / ML Models

nnU-Net

Self-configuring framework for medical image segmentation that automatically adapts its architecture, preprocessing, training, and post-proc…

↗ reposwh
AI / ML Models

OpenMed

Production-ready medical NLP toolkit providing state-of-the-art encoder transformers (BERT, ELECTRA, DeBERTa families) for biomedical named …

↗ site↗ reposwh
AI / ML Models

TractSeg

Automated segmentation of 72 white matter fibre bundles from diffusion MRI tractograms, directly from raw peaks (fibre orientation distribut…

↗ reposwh
AI / ML Models

TxAgent

LLM-based AI agent for therapeutic reasoning that orchestrates 211 biomedical tools spanning drug databases, genomic repositories, clinical …

↗ site↗ repo
Software

3D Slicer

Free, open-source platform for medical image informatics, image processing, and three-dimensional visualisation. Supports segmentation, regi…

↗ site↗ reposwh
Software

BBMRI-ERIC Negotiator

Open-source access negotiation platform for biobank and research infrastructure data requests. Manages the full Data Access Request (DAR) li…

↗ site↗ reposwh
Software

Biomni

General-purpose biomedical AI agent framework from Stanford SNAP Lab. Combines LLM reasoning with retrieval-augmented planning and code exec…

↗ site↗ reposwh
Software

CARE

FHIR R5-powered, modular open-source electronic health management information system (HMIS) developed by Open Healthcare Network Foundation …

↗ site↗ repo
Software

DIRECT

PyTorch-based deep learning framework for accelerated MRI reconstruction from undersampled k-space data. Implements a range of state-of-the-…

↗ site↗ reposwh
Software

Drug Named Entity Recognition

Lightweight Python library for identifying drug and medication names in free text, with fuzzy matching for misspellings and integration with…

↗ site↗ repo
Software

fMRIPrep

Robust and reproducible preprocessing pipeline for functional MRI (fMRI) data. Accepts BIDS-formatted input and performs brain extraction, s…

↗ site↗ reposwh
Software

GATK

The industry-standard toolkit for variant discovery in high-throughput sequencing data, developed by the Broad Institute. Implements best-pr…

↗ site↗ reposwh
Software

histolab

Python library for whole slide image (WSI) processing in computational pathology. Provides tissue detection, tiling, stain normalisation, an…

↗ site↗ reposwh
Software

Kaapana

Kubernetes-based open-source platform toolkit for building federated medical image analysis infrastructure. Orchestrates AI workflows (nnU-N…

↗ site↗ reposwh
Software

MedCAT

Clinical NLP toolkit for named entity recognition and linking in free-text clinical notes. Performs concept extraction and normalisation aga…

↗ site↗ reposwh
Software

MITK

Open-source medical image computing toolkit combining a full-featured desktop workbench for visualization, segmentation, and registration wi…

↗ site↗ reposwh
Software

MOLGENIS EMX2

FAIR research data platform for building and managing biobank catalogues, rare-disease registries, and cohort data portals. Provides a flexi…

↗ site↗ repo
Software

MONAI Model Zoo

Curated repository of 30+ production-ready medical imaging models in standardised MONAI Bundle format, covering segmentation, detection, cla…

↗ site↗ reposwh
Software

napari

Fast, interactive, multi-dimensional image viewer for Python. The standard viewer for bio-imaging and computational pathology workflows — su…

↗ site↗ reposwh
Software

NeuroKit2

Python library for neurophysiological signal processing. Provides accessible, reproducible tools for ECG, EEG, EMG, EDA, and PPG signals — c…

↗ site↗ reposwh
Software

OMERO

Open-source platform for managing, visualising, and analysing microscopy image data. Supports 150+ imaging formats, centralised storage, web…

↗ site↗ reposwh
Software

OpenMRS

Enterprise electronic medical record system platform used in resource-constrained environments worldwide.

↗ site↗ reposwh
Software

OpenScribe

Open-source, local-first AI clinical scribe that records patient encounters and automatically generates structured clinical notes. Runs enti…

↗ repo
Software

PathML

Open-source toolkit for computational pathology from Dana-Farber Cancer Institute. Covers the full digital pathology pipeline: whole slide i…

↗ site↗ reposwh
Software

pydicom

The standard Python library for reading, modifying, and writing DICOM files. Used in virtually every Python-based medical imaging pipeline —…

↗ site↗ reposwh
Software

PyHealth

Open-source Python toolkit for clinical deep learning that unifies datasets, tasks, and ML models across EHR, physiological signals, and med…

↗ site↗ reposwh
Software

RDKit

Open-source cheminformatics toolkit for molecule manipulation, descriptor calculation, substructure searching, and pharmacophore analysis. T…

↗ site↗ reposwh
Software

SimVascular

End-to-end open-source platform for patient-specific cardiovascular blood flow simulation. Provides a complete pipeline from medical image s…

↗ site↗ reposwh
Software

SlicerIGT

3D Slicer extension providing a toolkit for image-guided interventions (IGT). Offers real-time instrument tracking, ultrasound and needle gu…

↗ site↗ reposwh
Software

STIR

Leading open-source library for PET and SPECT tomographic image reconstruction. Provides iterative and analytical reconstruction algorithms,…

↗ site↗ reposwh
Software

Talk2Biomodels

AI agent framework for natural-language querying of systems biology models from the BioModels database (EMBL-EBI). Enables researchers to in…

↗ site↗ repo
Software

TotalSegmentator

Automated segmentation of more than 100 anatomical structures in CT and MR images using nnU-Net-based models. Covers bones, muscles, organs,…

↗ repo
Software

vantage6

Privacy Enhancing Technology (PET) operations platform enabling federated learning and multi-party computation across distributed healthcare…

↗ site↗ reposwh
Specs

FAIR Data Point (FDP) Specification

W3C Unofficial Proposal Draft specification for a metadata service that exposes digital objects following FAIR principles (Findable, Accessi…

↗ site↗ reposwh
Specs

HL7 FHIR R4

The dominant healthcare interoperability standard, defining a RESTful API and JSON/XML resource formats for exchanging clinical and administ…

↗ site
Specs

HealthDCAT-AP

The official EU metadata specification for describing health datasets for secondary use, extending DCAT-AP 3.0 with health-domain semantics.…

↗ site↗ repo
Specs

ODRL

W3C recommendation for expressing policies over data assets — permissions, prohibitions, and obligations. In healthcare, used to encode data…

↗ site
Specs

openEHR

Open specification for a vendor-neutral EHR platform based on a two-level modelling paradigm — separating stable technical architecture from…

↗ site↗ reposwh

Browse all entries on GitHub  ·  Contribute an entry

How it works

Git-native,
issue-driven curation

All catalog data lives as JSON-LD files in the repository. Suggest an entry via a GitHub issue or the form below — curators handle the rest.

Step Action Who
01 Open an issue on GitHub or use the form below to suggest an entry Contributor
02 Fill in required fields and evidence links Contributor
03 CI validates JSON syntax, required fields, and duplicate identifiers — automated schema generation and validation planned for Phase 2 Automated
04 Curator reviews entry rationale and evidence quality Curator
05 Merge → site updated; structured exports (MLDCAT-AP, CodeMeta, Croissant, llms.txt) are Phase 2 automations Automated

We your support
and contributions!

Know a tool, model, or standard that should be here? Open an issue or suggest an entry below.

↗ Open an Issue on GitHub Suggest an entry below

Suggest an entry

Know a tool, model, dataset, or standard that belongs in MACH? Drop a link and a sentence — we will take it from there.

Thanks — we have received your suggestion and will review it. If you left an email we may follow up.

Browse the catalog on GitHub

All catalog data lives as open JSON-LD files in the repository. Watch for updates or read the contributing guide.

★ Star the repo if you find it useful — it helps others discover MACH.

↗ github.com/FORSE-H/MACH Contributing guide