EHDS Linked Health Data Portal

500+

Unique patients

21.2M

RDF triples

Clinical cohorts

MCP tools

Benchmark queries

MCP Connector

Connect any MCP-compatible AI agent — Claude, mcphost, or Python SDK — to query the data space.

Connect via SSE

SPARQL Explorer

Write and run SPARQL queries against the HealthDCAT-AP catalogue and FHIR-on-RDF clinical data.

Open SPARQL UI

Supplements

Benchmark queries, evaluation harness, FHIR-to-RDF pipeline, and annotation guide — all files from the paper.

Browse files

RAG Vector Store

Download the pre-built ChromaDB vector store for RAG-condition evaluation.

Download ChromaDB

Knowledge Graph

Explore the EHDS data space interactively — datasets, ODRL policies, and clinical relationships visualised as a force-directed graph.

Open Explorer

Datasets

Graph	Condition	SNOMED CT	Patients
`graph/diabetes`	Type 2 Diabetes Mellitus	44054006	40
`graph/hypertension`	Essential Hypertension	59621000	40
`graph/metabolic-syndrome`	Metabolic Syndrome	237602007	40
`graph/obesity`	Obesity	162864005	40
`graph/hyperlipidemia`	Hyperlipidemia	55822004	40
`graph/prediabetes`	Prediabetes	714628002	40
`graph/hypothyroidism`	Hypothyroidism	83664006	40
`graph/anemia`	Anemia	271737000	40
`graph/heart-failure`	Heart Failure	88805009	15
`graph/stroke`	Stroke	230690007	40
`graph/myocardial-infarction`	Myocardial Infarction	22298006	40
`graph/ischemic-heart-disease`	Ischaemic Heart Disease	414545008	40
`graph/atrial-fibrillation`	Atrial Fibrillation	49436004	40
`graph/dementia`	Dementia	52448006	0
`graph/anxiety`	Anxiety	80583007	10
`graph/ptsd`	PTSD	47505003	10
`graph/alzheimers`	Alzheimer's Disease	26929004	40
`graph/osteoporosis`	Osteoporosis	64859006	40
`graph/rheumatoid-arthritis`	Rheumatoid Arthritis	69896004	38
`graph/chronic-kidney-disease`	Chronic Kidney Disease	431855005	40
`graph/asthma`	Asthma	195967001	28
`graph/copd`	COPD	87433001	40
`graph/sleep-apnea`	Sleep Apnea	73430006	40
`graph/uti`	Urinary Tract Infection	197927001	40
`graph/breast-cancer`	Breast Cancer	254837009	10
`graph/prostate-cancer`	Prostate Cancer	126906006	10
`graph/colorectal-cancer`	Colorectal Cancer	363406005	10
`graph/osteoarthritis`	Osteoarthritis	57676002	40
`graph/substance-use-disorder`	Substance Use Disorder	6525002	10
`graph/chronic-pain`	Chronic Pain	82423001	10
`graph/catalogue`	HealthDCAT-AP Release 5 metadata catalogue		—

Quick Start

Claude.ai: Settings → Connectors → Add custom connector

https://mcp.linkeddata.es/connector

mcphost:

echo '{"mcpServers":{"ehds":{"url":"https://mcp.linkeddata.es/connector"}}}' > ~/.mcp.json
mcphost -m ollama:llama3.2

Python:

from mcp import ClientSession
from mcp.client.sse import sse_client

async with sse_client("https://mcp.linkeddata.es/connector") as (r, w):
    async with ClientSession(r, w) as session:
        await session.initialize()
        result = await session.call_tool("ehds_list_datasets", {})

Citation

Manab et al. (2026). EHDS Linked Health Data Portal.
ISWC 2026 Resource Track. https://mcp.linkeddata.es