Return Kage proof metrics, or set mode=memory_quality / memory_scale for synthetic memory retrieval benchmarks.
AI agents call kage_benchmark to retrieve information from Kage without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The primary function is returning/reading metrics and benchmark data. The 'set mode' aspect could imply a configuration write, but in context it appears to control what metrics are returned rather than persistently changing system state. Classified as Read with moderate confidence since the 'set mode' language introduces some ambiguity about side effects.
From the tool's definition Return Kage proof metrics, or set mode=memory_quality / memory_scale for synthetic memory retrieval benchmarks
Documented attack patterns abuse exactly the kind of access kage_benchmark gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Kage, and nothing reaches the server without passing your rules. This is the rule we recommend for kage_benchmark:
{
"version": "1",
"default": "deny",
"tools": {
"kage_benchmark": {}
}
}kage_benchmark 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.
Return Kage proof metrics, or set mode=memory_quality / memory_scale for synthetic memory retrieval benchmarks. It is categorised as a Read tool in the Kage MCP Server, which means it retrieves data without modifying state.
Register the Kage MCP server in PolicyLayer and add a rule for kage_benchmark: 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 Kage. Nothing to install.
kage_benchmark 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 kage_benchmark 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 kage_benchmark. 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.
kage_benchmark is provided by the Kage MCP server (@kage-core/kage-graph-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Kage, 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.
62 Kage tools catalogued and risk-classified — across an index of 43,000+ MCP servers.