AI agents call schema to retrieve information from THOUGHT without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays schema information from the knowledge base without side effects. It is a query/inspection operation that does not alter state, execute code, or affect data. The low severity reflects minimal blast radius if called inappropriately by an AI agent—it merely exposes structural metadata about the system.
From the tool's definition Tool description: 'Show entity types and relation types currently in the KB.' The verb 'show' indicates read-only introspection of schema metadata. No data creation, modification, deletion, or execution occurs.
Attacks that exploit this kind of access
Show entity types and relation types currently in the KB. It is categorised as a Read tool in the THOUGHT MCP Server, which means it retrieves data without modifying state.
Register the THOUGHT MCP server in PolicyLayer and add a rule for 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 THOUGHT. Nothing to install.
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 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 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.
schema is provided by the THOUGHT MCP server (rnbbarrett/thought-mcp). 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 →