AI agents call kg_stats to retrieve information from Predicate without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
kg_stats retrieves and queries metadata about the knowledge graph state. It has no side effects, does not create, modify, or delete data, and does not execute arbitrary operations. This is a straightforward read operation that gathers statistics for monitoring or informational purposes.
From the tool's definition Tool returns graph statistics and counts (triples, abox, inferred, tbox, inferredRatio, unusedConceptRatio, materializationLatencyMsP95) with no modification capabilities mentioned.
Attacks that exploit this kind of access
Return current graph counts (triples, abox, inferred, tbox), inferredRatio, unusedConceptRatio, and materializationLatencyMsP95. It is categorised as a Read tool in the Predicate MCP Server, which means it retrieves data without modifying state.
Register the Predicate MCP server in PolicyLayer and add a rule for kg_stats: 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 Predicate. Nothing to install.
kg_stats 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 kg_stats 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 kg_stats. 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.
kg_stats is provided by the Predicate MCP server (nordicagents/predicate). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →