FHIR R4
Any HL7 FHIR R4 server: search and read Patients, Observations, Conditions, Encounters, MedicationRequests, DiagnosticReports and any other resource type, plus the server's own capability statement. Bearer-token auth.
7 días gratis · sin tarjeta · hosting UE
Pregunta cualquier cosa a FHIR
Prueba un prompt real contra FHIR R4 vía AnythingMCP — Claude llama a los tools y responde. Pulsa Enter en tu mensaje para instalar en Cloud.
Instalar FHIR en CloudClaude es IA y puede equivocarse. Verifica siempre las respuestas.
Setup en 2 minutos
- 1Inicia trial gratuita en cloud.anythingmcp.com.
- 2Click en FHIR R4 en el connector store. Pega las credenciales.
- 3Genera MCP API key y apunta el cliente AI a la URL MCP.
Guías para FHIR
Setup paso a paso para los principales clientes AI.
Configurar FHIR R4
Directamente de la definición del conector: dónde encontrar las credenciales, qué permisos necesitan y con qué API habla este adaptador. Proporcionadas en inglés por el autor del conector.
This is a generic FHIR R4 client, not a vendor connector. Point it at any R4 server — a hospital's HAPI instance, a national test server, a vendor's sandbox — and it speaks the standard.
- Set
FHIR_BASE_URLto the server's base, the URL that answers/metadata. No trailing slash. - Set
FHIR_ACCESS_TOKENto a bearer token. Most real deployments use SMART on FHIR, whose authorisation flow issues short-lived tokens; obtain one and paste it here, or use a long-lived service token if the server offers one. A server that needs no auth still needs a placeholder here — put anything.
Start with fhir_get_capability_statement. FHIR servers differ enormously in which resource types they hold and which search parameters they support, and /metadata is the machine-readable answer. Guessing produces a lot of confident 400s.
Search parameters are per resource type, and modifiers matter: name:contains=smith, birthdate=ge1980-01-01, code=http://loinc.org|85354-9, _lastUpdated=gt2026-09-01. Prefixes on numbers and dates are eq, ne, gt, lt, ge, le. A token search takes system|code, and the pipe is significant.
Results are a Bundle. The rows live in entry[].resource, the count in total (which some servers omit), and paging in link[] with relation: "next" — follow that URL rather than computing an offset. _count requests a page size; servers are free to ignore it.
_include and _revinclude fetch related resources in the same Bundle: _include=Observation:patient brings each observation's Patient along.
This is patient data. Anything read here is almost certainly health information under GDPR Article 9 or HIPAA. Whether an LLM may see it is a question about your legal basis and your processor agreements, not about this connector — decide it before installing, not after.
Read-only by design: no create, no update, no delete. A clinical record is not a thing an agent should write into by accident.
Tu IA está a dos clicks de FHIR R4.
Instala el conector, pega credenciales, pregunta a la IA. 7 días gratis, sin tarjeta.