HealthcareStudied

Wrap an EHR (FHIR R4) for a care agent

Read clinical data freely; propose orders — never auto-write.

Open the live lab · pre-loaded to this scenario

MCP Server Playground

Context

A care-coordination agent needs an EHR. The MCP server exposes read tools over encounters, labs, and meds, but the only mutation is a propose_order that returns pending clinician approval — PHI stays behind the server and nothing writes to the chart autonomously.

The decision

The design decision is which resources to expose and where the write-approval boundary sits: reads are broad, the single write is a proposal a human ratifies.

What most miss

Teams expose a write_order tool 'for convenience' and quietly hand an agent chart-write authority. The boundary is the whole safety design, not a feature flag.

Stakes

An autonomous chart write is a patient-safety and liability event; a proposal queued for a clinician is not.

Takeaway · Expose reads broadly; make every write a proposal a human ratifies.

Studied · Agent & Protocol · verified 2026-07-03

Sources: HL7 FHIR R4 resource model (encounters, observations, medications); Clinical human-in-the-loop / order-entry safety patterns

← All industries·See it in a full program storyline →