AI agents invoke fhir-request to trigger actions in Medplum MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
With an empty description, the exact behavior is unknown. However, 'fhir-request' on a FHIR server typically implies a generic HTTP request tool capable of any FHIR operation (GET, POST, PUT, DELETE, PATCH). Given sibling tools 'fetch' and 'search' handle read operations, 'fhir-request' likely handles write/execute/destructive operations.
From the tool's definition Tool name is 'fhir-request' with an empty description. The name suggests making FHIR API requests, which could encompass read, write, update, or delete operations on healthcare data.
Documented attack patterns abuse exactly the kind of access fhir-request gives an agent:
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 fhir-request:
{
"version": "1",
"default": "deny",
"tools": {
"fhir-request": {
"limits": [
{
"counter": "fhir-request_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}fhir-request stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
fhir-request. It is categorised as a Execute tool in the Medplum MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Medplum MCP Server MCP server in PolicyLayer and add a rule for fhir-request: 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.
fhir-request is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the fhir-request 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.
Set action: deny in the PolicyLayer policy for fhir-request. 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.
fhir-request is provided by the Medplum MCP Server MCP server (medplum/medplum-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
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.
3 Medplum MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.