AI agents call hermes_check to retrieve information from Hermes without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The name 'check' typically implies inspection or verification without modification. Given the empty description and naming convention aligned with 'ask', 'cancel', and 'reset' (which appear to be monitoring/control operations), this is most likely a Read operation that queries state or status. However, confidence is moderate due to lack of explicit documentation.
From the tool's definition Tool name 'hermes_check' suggests a query or status verification operation. Description is empty, providing no explicit evidence of side effects.
Documented attack patterns abuse exactly the kind of access hermes_check gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Hermes, and nothing reaches the server without passing your rules. This is the rule we recommend for hermes_check:
{
"version": "1",
"default": "deny",
"tools": {
"hermes_check": {}
}
}hermes_check 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.
hermes_check. It is categorised as a Read tool in the Hermes MCP Server, which means it retrieves data without modifying state.
Register the Hermes MCP server in PolicyLayer and add a rule for hermes_check: 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 Hermes. Nothing to install.
hermes_check 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 hermes_check 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 hermes_check. 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.
hermes_check is provided by the Hermes MCP server (mlennie/hermes-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Hermes, 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.
4 Hermes tools catalogued and risk-classified — across an index of 43,000+ MCP servers.