HealthClawGuardrails
UnclaimedOpen-source guardrails between AI agents and FHIR clinical data — PHI redaction, immutable audit, step-up auth, tenant isolation. MCP server + OpenAI/Gemini adapters. A healthclaw.io project.
Set up this server
More in Security
Browse the full directoryUnclaimed listing
Is this your MCP server?
This listing was auto-indexed from the public record. Claim it to edit the page, set compatibility and unlock growth tools. Takes under two minutes.
Claim this serverSecurity profile
Claimed and verified servers get a weekly static scan that shows what the code can reach: external services, environment variables, shell commands, agent configuration folders, plus any dependencies with known advisories. Claim this listing to get one. How the security profile works
25 of 25 tools
Documented tools (25)
From project documentation. A server handshake does not verify each tool’s description or behavior.
action_status
Poll a real-world action (call/SMS)
care_gaps
Preventive-care gaps ($care-gaps) — screenings/immunizations that may be due, from the patient's own records
context_get
Retrieve pre-built context envelopes
curatr_apply_fix
Apply patient-approved fixes with Provenance tracking
curatr_evaluate
Evaluate a FHIR resource for data quality issues
fetch
ChatGPT-connector-compatible fetch by ResourceType/id — thin wrapper over fhirread, returns {id, title, text, url, metadata}
fhir_commit_write
Commit with step-up auth + human-in-the-loop
fhir_compiled_truth
Current state + Provenance evidence timeline
fhir_get_token
Issue a 5-minute step-up token (call before any write)
fhir_interpret_labs
Lab reference-range interpretation ($interpret) — decision support, not diagnosis
fhir_lastn
Most recent N observations per code
fhir_permission_evaluate
R6 Permission access control evaluation
fhir_propose_write
Validate + preview without committing
fhir_read
Read a FHIR resource (redacted)
fhir_search
Search with patient, code, status, date filters
fhir_seed
Seed a tenant with demo Patient + Observations + Condition
fhir_stats
Observation statistics (count/min/max/mean)
fhir_subscription_topics
List available SubscriptionTopics
fhir_validate
Structural validation
guardrail_conformance
Run the guardrail conformance self-test — graded A–F scorecard across all seven properties
questionnaire_extract
SDC $extract — extract resources from a completed QuestionnaireResponse
questionnaire_populate
SDC $populate — pre-fill a Questionnaire for a subject
rx_transfer_request
Draft a pharmacy-transfer request call from active meds (Schedule II refused); commit via actioncommit
search
ChatGPT-connector-compatible search — thin wrapper over fhirsearch, returns compact {id, title, url} results
shl_generate
Generate an encrypted SMART Health Link (QR)
Tool change history
FAQ
Questions about HealthClawGuardrails MCP Server
- How do I connect HealthClawGuardrails MCP Server to Claude?
- The project does not publish a launch command that MCPVault could verify. Open the repository linked on this page for its install steps; the listing names Claude Desktop, Claude Code, ChatGPT as compatible clients.
- Is HealthClawGuardrails MCP Server free?
- The listed licence is MIT. Check the upstream terms for permitted use and commercial requirements; a public repository does not by itself mean the software is free or open source. Connected APIs and hosted services may have separate charges.
- What can HealthClawGuardrails MCP Server do?
- HealthClawGuardrails MCP Server documents 25 tools to the agent, including action_status, care_gaps, context_get. The descriptions above come from project documentation. A live handshake does not test individual tool behavior.