healthclaw-guardrails
Server Details
Guardrailed FHIR access for AI agents: PHI redaction, audit trail, step-up auth, tenant isolation
Glama couldn't complete the latest health check. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
- Status
- Unhealthy
- Uptime
- 0.0% over 38 days
- Last Tested
- Transport
- Streamable HTTP
- URL
- Repository
- aks129/HealthClawGuardrails
- GitHub Stars
- 30
- Server Listing
- HealthClawGuardrails
TDQS
Scored across 24 tools
Each tool has a clearly distinct purpose, with explicit descriptions that avoid overlap. The action_*, curatr_*, fhir_*, questionnaire_*, shl_*, sources_*, and wearables_* groups each cover unique functionality without ambiguity.
The naming follows a consistent prefix pattern (e.g., fhir_, curatr_), but within the fhir_ group there is inconsistency: some use verbs (read, search), others use nouns (stats, lastn, compiled_truth). This mix can cause slight confusion.
With 24 tools, the set is comprehensive for a health data guardrail server, covering FHIR operations, data quality, actions, questionnaires, SHL generation, and external source checks. The count is high but justified by the domain's complexity.
The tool set covers core operations: read, search, write (propose/commit), validate, statistics, lab interpretation, permission evaluation, data quality fixes, actions, questionnaires, SHL, and source checking. Missing explicit delete or update operations, but writing may encompass updates, and deletions may be out of scope.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
- Added
rx_transfer_request
1 tool update
- Added
care_gaps
1 tool update
- Added
guardrail_conformance
2 tool updates
- Added
fetch - Added
search
24 tool updates
- First observed
action_commit - First observed
action_propose - First observed
action_status - First observed
context_get - First observed
curatr_apply_fix - First observed
curatr_evaluate - First observed
fhir_commit_write - First observed
fhir_compiled_truth - First observed
fhir_get_token - First observed
fhir_interpret_labs - First observed
fhir_lastn - First observed
fhir_permission_evaluate - First observed
fhir_propose_write - First observed
fhir_read - First observed
fhir_search - First observed
fhir_seed - First observed
fhir_stats - First observed
fhir_subscription_topics - First observed
fhir_validate - First observed
questionnaire_extract - First observed
questionnaire_populate - First observed
shl_generate - First observed
sources_check - First observed
wearables_sync_status
Related MCP Connectors
AgentGuard — 20-tool AI safety MCP: policy preflight, risk scoring, audit logging, rate limits.
Security gateway for AI agents: policy, approval, and audited execution, no secrets shared.
HealthGuard - 12-tool health/medical AI safety MCP: PII redaction, HIPAA, GDPR Art.9.
- FullmaktOAuthai.fullmakt
Credential broker for AI agents: scoped, revocable API access with policy enforcement and audit.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables LLMs to securely interact with FHIR healthcare servers and HL7 terminology services. Provides comprehensive healthcare data operations with built-in PHI protection, audit logging, and SMART on FHIR authentication.MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI applications to securely search and manage healthcare data from FHIR R4-compliant servers with built-in safety validation for AI-generated clinical observations, preventing recording of physiologically impossible values.9 npm48 PyPIMIT
- AlicenseAqualityDmaintenanceEnables LLM-based agents to interact with FHIR healthcare data through natural language prompts, providing full CRUD operations on FHIR resources, document processing, and semantic search capabilities.13100MIT
- AlicenseNot gradedqualityAmaintenanceThe Zero-Trust Security & Privacy Gateway for AI Agents2Apache 2.0
Glama MCP Gateway
Add one secure layer between your agents and this server.