Compare the same task on the same repo with and without Kage. Reports estimated baseline discovery tokens/steps versus Kage recall/code-graph context, with evidence and caveats.
AI agents call kage_benchmark_compare 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.
This tool compares and reports benchmarking metrics between two configurations. It retrieves and presents estimates/comparisons with no indication of creating, modifying, executing, or deleting data. Pure read/reporting functionality.
From the tool's definition Compare the same task on the same repo with and without Kage. Reports estimated baseline discovery tokens/steps versus Kage recall/code-graph context, with evidence and caveats.
Documented attack patterns abuse exactly the kind of access kage_benchmark_compare 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_compare:
{
"version": "1",
"default": "deny",
"tools": {
"kage_benchmark_compare": {}
}
}kage_benchmark_compare 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.
Compare the same task on the same repo with and without Kage. Reports estimated baseline discovery tokens/steps versus Kage recall/code-graph context, with evidence and caveats. 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_compare: 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_compare 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_compare 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_compare. 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_compare 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.