# HL7 FHIR MCP Server & Agent Skill

> Source: https://ibl.ai/developer/connectors/fhir

Connector · Healthcare data exchange standard

Last updated: October 20, 2026

**ibl.ai publishes a free HL7 FHIR agent skill: a SKILL.md that teaches an AI agent to read and write HL7 FHIR data and expose it as an MCP tool. Download it, connect your own HL7 FHIR credentials, and run the agent on ibl.ai Agentic OS, where you own all the code and the data.**

FHIR (Fast Healthcare Interoperability Resources) is HL7's standard for exchanging health data as resources such as Patient, Observation and Condition over a REST API. R4 (4.0.1) is widely implemented; 5.0.0 is the current release.

## What is the HL7 FHIR API, and what can an agent read from it?

Defines read, vread, update, patch, delete, history, create, search, capabilities (GET [base]/metadata) and batch/transaction interactions on [base]/[type]/[id], in JSON, XML or Turtle.

- API: FHIR RESTful API (R4, 4.0.1) and SMART App Launch (FHIR R4)
- Access: Public, self-serve
- Base URL: [base]/[type]/[id] where [base] is each server's Service Base URL
- Authentication: SMART App Launch (OAuth 2.0 authorization code); SMART Backend Services (JWT)

The specification is free to read. Credentials come from each FHIR server operator (an EHR vendor or health system), usually by registering a SMART client.

SMART App Launch 2.2.0 defines EHR and standalone launch, discovery at .well-known/smart-configuration, and scopes like patient/Observation.rs. Backend Services use client_credentials with a jwt-bearer client assertion.

### What can an agent read from HL7 FHIR?

- **Read and vread** — GET [base]/[type]/[id] returns the current version; vread returns a specific version.
- **Search** — GET or POST search on a type; results come back as a Bundle of type searchset.
- **History** — History of changes at instance, type or system level.
- **Capabilities** — GET [base]/metadata returns the server's CapabilityStatement.

### What can an agent write to HL7 FHIR?

- **Create** — POST [base]/[type] creates a resource with a server-assigned id.
- **Update and patch** — PUT [base]/[type]/[id] replaces a resource (or creates it); PATCH changes part of it.
- **Delete** — DELETE [base]/[type]/[id]; later reads return 410 Gone. Confirm with the user first.
- **Batch and transaction** — POST a Bundle to [base] to run several operations, atomically for a transaction. Confirm with the user first.

Limits: Search results return as a Bundle of type searchset, paged with self, first, previous, next and last links. Backend Services access tokens SHOULD NOT exceed 300 seconds (expires_in).

FHIR is a format, not a data store, but records exchanged with US providers are usually HIPAA protected health information (PHI); servers enforce access with SMART scopes.

## How do I connect HL7 FHIR to an AI agent over MCP?

As of October 2026 we found no MCP server published by HL7 International itself.

The practical path is to host a small MCP server that wraps the FHIR RESTful API (R4, 4.0.1) and SMART App Launch, or to give the agent the calls directly with the SKILL.md below.

On ibl.ai an MCP connection is three records, and a working integration always needs all three:

1. **Register the server** — `POST …/mcp-servers/` with its URL, a transport (`sse`, `websocket` or `streamable_http`) and an `auth_type` of `none`, `token` or `oauth2`.
2. **Create a connection** that holds the credential, scoped to the whole organization (`platform`), to a single agent, or to each user (`user`).
3. **Enable it on the agent** — `mcp-tool` in `tool_slugs` and the server id in `mcp_servers`. Both lists are replaced, not merged, so read the settings first.

HL7 FHIR supports per-user OAuth, so the server can use `auth_type=oauth2` with `auth_scope=user`: each person connects their own HL7 FHIR account in the chat the first time the agent needs it.

The field reference is in [MCP server connections](https://ibl.ai/developer/platform/mcp/mcp-connections), and the [/iblai-api-agent-mcp](https://ibl.ai/developer/skills/iblai-api-agent-mcp) skill runs all three steps from a coding agent.

## What does the HL7 FHIR agent skill do?

The HL7 FHIR skill is one SKILL.md file named `iblai-connect-fhir`. It gives an agent the auth conventions, what to read, which writes need a person's confirmation, the ibl.ai MCP wiring, example prompts and guardrails.

[Download the HL7 FHIR SKILL.md](https://ibl.ai/developer/connectors/fhir/SKILL.md)

Save it as `.claude/skills/iblai-connect-fhir/SKILL.md`, or in your agent's skills folder. The ibl.ai platform skills it calls come from one install:

```
npx skills add iblai/vibe --all
```

This connector skill is a starting point maintained on ibl.ai, not part of the iblai/vibe repository.

It was checked against HL7 International's documentation on October 20, 2026. Test it against your own HL7 FHIR setup before you rely on it.

### What can I ask an HL7 FHIR agent to do?

- “Read this FHIR server's CapabilityStatement and tell me which resources it supports.”
- “Search Observation for LOINC 4548-4 for patient 123 and chart the results.”
- “Build a transaction Bundle that creates this Patient and two Conditions.”
- “Check the server's SMART configuration and list supported scopes.”

## How do I run an HL7 FHIR agent on ibl.ai?

[Agentic OS](https://ibl.ai/product/agentic-os) is where the agent runs on ibl.ai: it holds the HL7 FHIR MCP connection, the model the agent uses, its instructions and its conversation history.

On ibl.ai you own all the code and the data, run it model-agnostic across any LLM, and pay with no per-seat pricing — so you can deploy anywhere, from your own cloud to a fully air-gapped network.

- [AI agents for Healthcare](https://ibl.ai/solutions/medical-healthcare) — what ibl.ai deploys in this sector

### Which ibl.ai agents work with HL7 FHIR data?

- [Clinical Support](https://ibl.ai/solutions/medical-healthcare/agent/clinical-support-agent) — Healthcare
- [Care Coordination](https://ibl.ai/solutions/medical-healthcare/agent/care-coordination-agent) — Healthcare
- [Research](https://ibl.ai/solutions/medical-healthcare/agent/research-agent) — Healthcare

### Which ibl.ai platform skills does an HL7 FHIR agent use?

- [/iblai-api-agent-mcp](https://ibl.ai/developer/skills/iblai-api-agent-mcp) — MCP connectors for ibl.ai agents, end to end
- [/iblai-vibe-agent-mcp](https://ibl.ai/developer/skills/iblai-vibe-agent-mcp) — Add the agent MCP tab (Model Context Protocol connector management with featured connectors, custom connectors, OAuth,…
- [/iblai-api-agent-tool](https://ibl.ai/developer/skills/iblai-api-agent-tool) — Enable or disable an ibl.ai agent's tools via the platform API

## What else should I know before connecting HL7 FHIR to an AI agent?

### Is there an official HL7 FHIR MCP server?

Not that we found as of October 20, 2026: HL7 International documents the FHIR RESTful API (R4, 4.0.1) and SMART App Launch, not an MCP server of its own.

The SKILL.md on this page gives an agent the integration directly, and any MCP server you host can be registered on ibl.ai.

### Who can get HL7 FHIR API credentials?

The specification is free to read. Credentials come from each FHIR server operator (an EHR vendor or health system), usually by registering a SMART client.

### Does HL7 FHIR data leave my infrastructure when an ibl.ai agent uses it?

On ibl.ai, you own all the code and the data. Self-hosted in your cloud or data center, the agent, its MCP connections and its conversation logs stay inside your perimeter.

Because the platform is model-agnostic, you can point the agent at a model you host, so HL7 FHIR records need not reach a third-party model provider.

### Is the HL7 FHIR agent skill free to use?

Yes. The SKILL.md is a free download with no sign-up. It assumes you already have HL7 FHIR credentials, and your agreement with HL7 International still governs how you use its API.

## Which other data sources can an AI agent connect to alongside HL7 FHIR?

### Which other Healthcare systems have a connector?

- [athenahealth](https://ibl.ai/developer/connectors/athenahealth) — Cloud EHR and practice management
- [Availity](https://ibl.ai/developer/connectors/availity) — Payer-provider health information network
- [Epic](https://ibl.ai/developer/connectors/epic) — Electronic health record (EHR)
- [MEDITECH Expanse](https://ibl.ai/developer/connectors/meditech) — Electronic health record (EHR)
- [Oracle Health (Cerner)](https://ibl.ai/developer/connectors/oracle-health-cerner) — Electronic health record (EHR)
- [Veradigm](https://ibl.ai/developer/connectors/veradigm) — Electronic health record (EHR)

Every connector, grouped by sector, is on the [connectors hub](https://ibl.ai/developer/connectors).
