Medium Risk

createObservation

Creates a new observation (lab result, vital sign, etc.). Requires patient ID and code.

How to control createObservation ↓

What createObservation does on Medplum MCP Server

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

Medium Risk

Why createObservation needs a policy

This tool creates new medical observation records (lab results, vital signs) in a healthcare database. It is a Write operation as it irreversibly adds data to the system. Severity is high because incorrect observations could lead to clinical decisions based on false medical data, affecting patient care and safety.

From the tool's definition Tool name 'createObservation' and description states it 'Creates a new observation' - explicitly creates new healthcare data in a FHIR server.

Documented attack patterns abuse exactly the kind of access createObservation gives an agent:

How to control createObservation

PolicyLayer is an MCP gateway — it sits between your AI agents and Medplum MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for createObservation:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "createObservation": {
      "limits": [
        {
          "counter": "createobservation_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

createObservation 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.

  1. Create a free account and register Medplum MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about createObservation

What does the createObservation tool do? +

Creates a new observation (lab result, vital sign, etc.). Requires patient ID and code. It is categorised as a Write tool in the Medplum MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on createObservation? +

Register the Medplum MCP Server MCP server in PolicyLayer and add a rule for createObservation: 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 Medplum MCP Server. Nothing to install.

What risk level is createObservation? +

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

Can I rate-limit createObservation? +

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

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

createObservation is provided by the Medplum MCP Server MCP server (rkirkendall/medplum-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Medplum MCP Server tool call.

Start from Medplum MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

37 Medplum MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.