AI agents invoke eval_record to trigger actions in Smart EHR 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.
The prefix 'eval' conventionally indicates evaluation or execution of dynamic expressions/code. In the context of an EHR system handling sensitive patient data, an eval-type operation could execute arbitrary logic against medical records. The empty description lowers confidence, but the naming pattern combined with the high-sensitivity medical context warrants a high severity rating.
From the tool's definition Tool name 'eval_record' — 'eval' strongly implies evaluation/execution of code or expressions; description is empty and uninformative.
Documented attack patterns abuse exactly the kind of access eval_record gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Smart EHR MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for eval_record:
{
"version": "1",
"default": "deny",
"tools": {
"eval_record": {
"limits": [
{
"counter": "eval_record_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}eval_record 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.
eval_record. It is categorised as a Execute tool in the Smart EHR MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Smart EHR MCP Server MCP server in PolicyLayer and add a rule for eval_record: 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 Smart EHR MCP Server. Nothing to install.
eval_record 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 eval_record 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 eval_record. 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.
eval_record is provided by the Smart EHR MCP Server MCP server (jmandel/health-record-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Smart EHR 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.
6 Smart EHR MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.