AI agents call fetch to retrieve information from Medplum MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'fetch' operation in a FHIR context retrieves healthcare data without modifying or deleting it. While healthcare data is sensitive, the tool itself performs read-only retrieval operations. The primary risk is information disclosure rather than destructive or operational changes. Severity is low because the tool does not execute arbitrary commands, delete data, or move money—it simply retrieves existing records.
From the tool's definition Tool name is 'fetch', which is a standard operation for retrieving data. The sibling tool 'search' and overall server context (Medplum FHIR data access) confirms this is a data retrieval operation. No description provided, which lowers confidence slightly.
Documented attack patterns abuse exactly the kind of access fetch 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 fetch:
{
"version": "1",
"default": "deny",
"tools": {
"fetch": {}
}
}fetch is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
fetch. It is categorised as a Read tool in the Medplum MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Medplum MCP Server MCP server in PolicyLayer and add a rule for fetch: 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.
fetch is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the fetch 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 fetch. 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.
fetch 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.