Healthclaw Guardrails
HealthClaw Guardrails is the security layer between AI agents and clinical FHIR data. Every agent read passes through PHI redaction (names truncated to initials, DOBs to year, identifiers masked). Every write requires an HMAC-signed step-up token with a 5-minute TTL. Clinical writes (Condition, MedicationRequest, DiagnosticReport) return HTTP 428 until a human confirms. Every access lands in an append-only audit trail scoped by tenant. Supports FHIR R4 US Core v9 (stable) and FHIR R6 v6.0.0-bal
Works with: Claude Code, Cursor, Claude Desktop, Codex CLI, Gemini CLI, Cline, Windsurf, VS Code
Category: Security — see all ranked ›
Work: Regulatory compliance · Security review · Agent configuration
Who it is for: Legal / compliance · Security engineer · Agent operator
“Demo server is hard-pinned to synthetic data; 29 tools sit under walls of release notes”
- tashan score: 62.0
- Expertise: 74.0 (solid)
- Adoption: 1 repos
- Health: active
- GitHub stars: 27
- Contributors: 7
- License: MIT
Security audit
Not scanned yet. We audit npm-published capabilities for known advisories, install-time scripts and permission surface; this one has no npm package we can resolve, or has not reached the queue.
source ↗ · plugin:aks129/healthclawguardrails/healthclaw-guardrails
Already running this? npx tashan-cli doctor checks your whole config against the Index — how it works ›