HealthClaw

HealthClaw is a guardrail layer between AI agents and clinical FHIR data, with PHI redaction and audit trails.

aks129 22
Claude CodeClaude DesktopGeneric
View source ↗

HealthClaw provides guardrailed access to FHIR health records for AI agents, redacting protected health information, enforcing deny-by-default permissions, and logging an immutable audit trail of every access. It supports step-up authentication and tenant isolation, and works with any FHIR server including Epic, Medplum, and HAPI.

Connection

  • streamable_http · auth: open · free — https://mcp-server-production-5112.up.railway.app/mcp

Source

Repository: https://github.com/aks129/healthclawguardrails

Maintain HealthClaw?

Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.

[HealthClaw on getagentictools](https://getagentictools.com/mcp/aks129-healthclawguardrails?ref=badge)