fhir.update · Fhir MCP: Risk & Policy

WHAT IT DOES

What fhir.update does on FhirMCP

AI agents use fhir.update to create or update resources in FhirMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your FhirMCP environment.

WHY IT NEEDS A POLICY

Why fhir.update needs a policy

This tool modifies healthcare data reversibly by updating FHIR resources. It is not destructive (does not delete), not execute (does not run arbitrary code), and not financial. However, the 'high' severity reflects that healthcare data (PHI/PII) is highly sensitive—unauthorized updates could compromise patient safety, privacy, and data integrity.

From the tool's definition Tool name 'fhir.update' and description 'Update an existing FHIR resource (requires write permissions)' clearly indicate modification of existing healthcare data records.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

fhir.update Rate-limited

fhir.update stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "fhir.update": {
      "limits": [
        {
          "counter": "fhir.update_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches FhirMCP, so you can run agents against it safely.

FAQ

Questions about fhir.update

What does the fhir.update tool do? +

Update an existing FHIR resource (requires write permissions). It is categorised as a Write tool in the FhirMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on fhir.update? +

Register the Fhir MCP server in PolicyLayer and add a rule for fhir.update: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches FhirMCP. Nothing to install.

What risk level is fhir.update? +

fhir.update is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit fhir.update? +

Yes. Add a rate_limit block to the fhir.update rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block fhir.update completely? +

Set action: deny in the PolicyLayer policy for fhir.update. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides fhir.update? +

fhir.update is provided by the Fhir MCP server (xsovx/fhir-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.