Skip the install. Get this working in under 2 minutes.
Start a free trial on cloud.anythingmcp.com, add the FHIR R4 in one click, then point your AI client (Claude, ChatGPT, Copilot or Cursor) at the generated MCP endpoint. No Docker, no git clone, zero engineering experience required.
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.
Try asking
Example prompts for FHIR R4
Click any prompt to copy it. Paste into Claude, ChatGPT, Cursor, Gemini, Copilot or OpenClaw to run it against this connector.
Claude is AI and can make mistakes. Please double-check responses.
💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → FHIR R4, paste your credentials, mint an MCP API key — done. No Docker, no
git clone, no local server.
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.
Prerequisites
See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:
FHIR_BASE_URL, FHIR_ACCESS_TOKEN
Step 1 — Get credentials
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 — Install the 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 — Add the connector in Gemini
Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (
https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide showsYOUR_SERVER_ID.
Gemini CLI reads MCP servers from ~/.gemini/settings.json (or %APPDATA%\gemini\settings.json on Windows). Add:
{
"mcpServers": {
"anythingmcp": {
"httpUrl": "https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID",
"headers": { "X-API-Key": "YOUR_MCP_API_KEY" }
}
}
}
- Get your MCP API key from AnythingMCP → MCP Servers → your server → API keys.
- Save the file and restart
gemini. - Run
/mcpinside the Gemini CLI —FHIR R4should be listed as available. - Vertex AI Studio: pass
https://cloud.anythingmcp.com/mcp/YOUR_SERVER_IDto thetoolsarray of your request with the sameX-API-Keyheader.
Available tools
| 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 |
fhir_next_page | Fetch the next page of a search result |
FAQ
Does Gemini 1.5 Pro or 2.x support MCP? Yes — Gemini CLI ≥ 0.4 and Vertex AI tools API both accept MCP httpUrl connectors with custom headers.
Next steps
Was this guide helpful?
