Skip to main content
Glama

Server Details

HL7 FHIR R4 health-data API for AI agents: free sandbox, 30 synthetic patients, AI-ready context.

The last two health checks of this connector failed. 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
0.7% over 21 days
OAuth
Not checked
Last Tested
Transport
Streamable HTTP
URL

TDQS

A3.6/5.0

Scored across 14 tools

Disambiguation4/5

Most tools target distinct actions (create, read, search, validate, list, reset). The get_patient_* family (context, summary, timeline, provenance) and list_patients vs search_fhir on Patient are the only mild overlaps, and the descriptions explicitly clarify boundaries (e.g. 'to filter use search_fhir on Patient'). create_patient vs create_fhir_resource is a minor convenience overlap but reasonably distinct.

Naming Consistency4/5

Almost all names follow a consistent verb_noun snake_case pattern (create_fhir_resource, read_fhir_resource, get_patient_context, search_fhir, validate_fhir_resource). The only deviation is the noun-only sandbox_status, a small inconsistency that doesn't impede readability.

Tool Count5/5

14 tools is well within the sweet spot for a FHIR sandbox server. Each tool covers a distinct capability (validation, creation, reading, search, import, context building, provenance, sandbox administration) and none feels redundant or padding.

Completeness3/5

Create, read, search, validate, import and context-building are all covered, but there is no update or delete operation for existing FHIR resources, which is a notable gap for a record-manipulation surface. Import and validation mitigate this partially, but agents cannot modify or remove records after creation.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 14 tool updates
    • First observedcreate_fhir_resource
    • First observedcreate_patient
    • First observedget_patient_context
    • First observedget_patient_summary
    • First observedget_provenance
    • First observedget_timeline
    • First observedimport_lab_report
    • First observedlist_patients
    • First observedlookup_code
    • First observedread_fhir_resource
    • First observedreset_sandbox
    • First observedsandbox_status
    • First observedsearch_fhir
    • First observedvalidate_fhir_resource

Related MCP Connectors

Related MCP Servers

  • A
    license
    A
    quality
    C
    maintenance
    Provides safe read-only access to synthetic healthcare data via FHIR R4, enabling AI assistants to search patients, retrieve vitals, and summarize conditions using a public sandbox.
    4
    33 npm
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Connects frontier AI agents to HL7 FHIR R4 electronic health record repositories, enabling patient, observation, condition, medication, allergy, and diagnostic report queries plus draft-only clinical writes. Enforces mathematical safety gates, HIPAA-compliant tamper-evident audit logging, and token distillation of bulky FHIR payloads.
    Apache 2.0
  • F
    license
    Not graded
    quality
    A
    maintenance
    Enables LLM-based agents to connect to a FHIR-compliant healthcare backend and query or manipulate clinical data with natural-language prompts. Provides full CRUD operations on FHIR resources, AI-powered document ingestion and semantic search, RAG-ready retrieval, and LOINC terminology lookup.
    -
Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources