propose_observation · Fhir Synthetic MCP: Risk & Policy

WHAT IT DOES

What propose_observation does on Fhir Synthetic

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

WHY IT NEEDS A POLICY

Why propose_observation needs a policy

This tool creates or modifies data (a new observation proposal) but explicitly does not finalize the write—it stages the change for human review and approval. This is a classic Write pattern with compensating controls (human gating, audit logging, ability to reject). The impact is reversible until approved, and even then subject to human oversight.

From the tool's definition Tool name 'propose_observation' and description 'Propose a new observation. Stages it for human approval; does NOT write.' indicate creation of a reversible, staged change (proposal) that requires human approval before commitment.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

propose_observation Rate-limited

propose_observation 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": {
    "propose_observation": {
      "limits": [
        {
          "counter": "propose_observation_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 Fhir Synthetic, so you can run agents against it safely.

FAQ

Questions about propose_observation

What does the propose_observation tool do? +

Propose a new observation. Stages it for human approval; does NOT write. It is categorised as a Write tool in the Fhir Synthetic MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on propose_observation? +

Register the Fhir Synthetic MCP server in PolicyLayer and add a rule for propose_observation: 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 Fhir Synthetic. Nothing to install.

What risk level is propose_observation? +

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

Can I rate-limit propose_observation? +

Yes. Add a rate_limit block to the propose_observation 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 propose_observation completely? +

Set action: deny in the PolicyLayer policy for propose_observation. 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 propose_observation? +

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