Sáltate la instalación. Funcionando en menos de 2 minutos.
Inicia una prueba gratuita en cloud.anythingmcp.com, añade FHIR R4 con un clic y apunta tu cliente de IA (Claude, ChatGPT, Copilot o Cursor) al endpoint MCP generado. Sin Docker, sin git clone, sin experiencia de desarrollo.
Summary
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.
Prueba a pedir
Prompts de ejemplo para FHIR R4
Haz clic en un prompt para copiarlo. Pégalo en Claude, ChatGPT, Cursor, Gemini, Copilot u OpenClaw para ejecutarlo contra este conector.
Claude es IA y puede equivocarse. Verifica siempre las respuestas.
💡 ¿Sin instalación? Usa cloud.anythingmcp.com directamente. Inicia sesión, pulsa Connectors → FHIR R4, pega tus credenciales, genera una MCP API key — listo. Sin Docker, sin
git clone, sin servidor local.
FHIR R4 + Gemini
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.
Requisitos previos
Las instrucciones de configuración completas están incluidas en el conector (visibles en el store al seleccionarlo). Las variables de entorno requeridas:
FHIR_BASE_URL, FHIR_ACCESS_TOKEN
Paso 1 — Obtener credenciales
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.
…(continued in the in-app connector instructions)
Paso 2 — Instalar el adapter
curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d
Paso 3 — Añadir el conector en Gemini
Gemini CLI lee servidores MCP desde ~/.gemini/settings.json (o %APPDATA%\gemini\settings.json en Windows). Añade:
{
"mcpServers": {
"anythingmcp": {
"httpUrl": "https://cloud.anythingmcp.com/mcp",
"headers": { "Authorization": "Bearer YOUR_MCP_API_KEY" }
}
}
}
- Obtén tu MCP API key desde AnythingMCP → Perfil → MCP API Keys → Nueva Key.
- Guarda el archivo y reinicia
gemini. - Ejecuta
/mcpen la Gemini CLI —FHIR R4debería aparecer como disponible. - Vertex AI Studio: pasa
https://cloud.anythingmcp.com/mcpal arraytoolsde tu petición con el mismo header Bearer.
Herramientas disponibles
| Tool | What it does |
|---|---|
fhir_get_capability_statement | Read the server's CapabilityStatement: which resource types it holds, which interactions and search parameters each supports, and its FHIR v |
fhir_search | Search any resource type with FHIR's standard parameters |
fhir_read_resource | Read one resource instance by type and id, returning the full resource rather than a Bundle entry |
fhir_search_patients | Search Patients by name, identifier, birth date or family name |
fhir_get_patient_observations | Read the Observations recorded for one patient — vital signs, laboratory results, measurements — optionally narrowed to one LOINC code or ca |
fhir_get_patient_conditions | Read the Conditions recorded for one patient — the problem list — with their clinical and verification status |
fhir_get_patient_encounters | Read the Encounters for one patient — admissions, visits and consultations — with their class, period and the practitioners involved |
fhir_get_patient_medications | Read the MedicationRequests for one patient — what has been prescribed, in what dosage, by whom and with what status |
fhir_get_patient_reports | Read the DiagnosticReports for one patient — laboratory panels, imaging reports and pathology — with their category, status and conclusions |
fhir_get_patient_everything | Run the $everything operation on one patient: every resource the server associates with them, in one Bundle |
FAQ
¿Gemini 1.5 Pro o 2.x soportan MCP? Sí — Gemini CLI ≥ 0.4 y la API de tools de Vertex AI aceptan conectores MCP httpUrl con header Bearer.
Siguientes pasos
¿Te ha sido útil esta guía?
