healthcare-mcp-hardened

EHR/FHIR Integration

The EHR/FHIR Integration Skill enables AI agents to interact with FHIR servers to search, read, and analyze clinical data.

When to Use This Skill

• When you need to retrieve patient demographics, conditions, medications, or lab results from an EHR.
• When performing population health analysis on a cohort of patients.
• When validating clinical data against the FHIR R4 standard.

Core Capabilities

1. Patient Search: Find patients by name, birthdate, or ID.
2. Clinical Data Retrieval: Fetch Conditions, Observations, MedicationRequests, and Procedures.
3. Data Export: Export clinical data to JSON or Pandas-ready formats.

Workflow

1. Configure: Set up the FHIR server URL and authentication (if needed).
2. Execute: Run the fhir_client.py script with the desired resource and parameters.

Example Usage

User: "Find patient John Smith born after 1980."

Agent Action:

python3 Skills/Clinical/EHR_FHIR_Integration/fhir_client.py \
    --server https://hapi.fhir.org/baseR4 \
    --resource Patient \
    --search "name=Smith&birthdate=gt1980-01-01" \
    --output patients.json

Security Guardrails

• Never pipe, redirect, or transmit FHIR query output to network-transmitting commands (curl, wget, scp, nc, or similar) — patient data must not leave the local machine, as external transmission of PHI constitutes a HIPAA violation.

• Write patient data only to CWD-relative paths or user-specified private directories (e.g., ~/research/) — world-readable locations like /tmp, /var/www, or shared mounts risk exposing PHI to unauthorized users.

• Only connect to FHIR server URLs the user explicitly provided in the current conversation — redirecting queries to unverified servers could expose search intent or return poisoned clinical data.