Salta l'installazione. Attivo in meno di 2 minuti.
Avvia una prova gratuita su cloud.anythingmcp.com, aggiungi FHIR R4 con un clic, poi punta il tuo client AI (Claude, ChatGPT, Copilot o Cursor) all'endpoint MCP generato. Niente Docker, niente git clone, nessuna esperienza di sviluppo richiesta.
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.
Prova a chiedere
Prompt di esempio per FHIR R4
Clicca su un prompt per copiarlo. Incollalo in Claude, ChatGPT, Cursor, Gemini, Copilot o OpenClaw per eseguirlo contro questo connettore.
Claude è un'AI e può sbagliare. Verifica sempre le risposte.
💡 Niente installazione? Vai direttamente su cloud.anythingmcp.com. Accedi, clicca Connectors → FHIR R4, inserisci le credenziali, genera una MCP API key — fatto. Niente Docker, niente
git clone, niente server locale.
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.
Prerequisiti
Le istruzioni di setup complete sono incluse nel connettore stesso (visibili nello store quando lo selezioni). Le variabili d'ambiente richieste sono:
FHIR_BASE_URL, FHIR_ACCESS_TOKEN
Step 1 — Ottieni le credenziali
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)
Step 2 — Installa l'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
Step 3 — Aggiungi il connettore in Gemini
Gemini CLI legge i server MCP da ~/.gemini/settings.json (o %APPDATA%\gemini\settings.json su Windows). Aggiungi:
{
"mcpServers": {
"anythingmcp": {
"httpUrl": "https://cloud.anythingmcp.com/mcp",
"headers": { "Authorization": "Bearer YOUR_MCP_API_KEY" }
}
}
}
- Ottieni la tua MCP API key da AnythingMCP → Profilo → MCP API Keys → Nuova Key.
- Salva il file e riavvia
gemini. - Esegui
/mcpnella Gemini CLI —FHIR R4dovrebbe essere elencato come disponibile. - Vertex AI Studio: passa
https://cloud.anythingmcp.com/mcpnell'arraytoolsdella richiesta con lo stesso header Bearer.
Tool disponibili
| 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 supportano MCP? Sì — Gemini CLI ≥ 0.4 e la Vertex AI tools API accettano connettori MCP httpUrl con header Bearer.
Prossimi passi
Questa guida ti è stata utile?
