AI agents call kg_explore_schema 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.
This tool queries and retrieves schema information (TBox - terminological box) from the knowledge graph. It performs no mutations, side effects, or external operations. It is a pure read operation analogous to schema inspection queries. Confidence is high because the description is explicit about the read-only nature of the operation.
From the tool's definition Tool name 'kg_explore_schema' and description 'Return the TBox slice (classes, sub/super, properties, characteristics) for a concept' indicate a retrieval operation. The verb 'Return' explicitly describes querying schema metadata without modification.
Attacks that exploit this kind of access
Return the TBox slice (classes, sub/super, properties, characteristics) for a concept. 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_explore_schema: 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_explore_schema 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_explore_schema 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_explore_schema. 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_explore_schema 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 →