discover_models_for_question
AI agents call discover_models_for_question to retrieve information from Ai Analyst without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to discover or retrieve available models relevant to a user's question—a data retrieval operation with no side effects. Without a description, confidence is moderate. The naming convention and context (product analytics server with query-focused tools) support classifying this as a Read operation with low severity.
From the tool's definition Tool name 'discover_models_for_question' suggests querying or retrieving model metadata to answer a question. No description provided, but the name pattern aligns with discovery/retrieval operations.
Attacks that exploit this kind of access
discover_models_for_question. It is categorised as a Read tool in the Ai Analyst MCP Server, which means it retrieves data without modifying state.
Register the Ai Analyst MCP server in PolicyLayer and add a rule for discover_models_for_question: 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 Ai Analyst. Nothing to install.
discover_models_for_question 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 discover_models_for_question 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 discover_models_for_question. 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.
discover_models_for_question is provided by the Ai Analyst MCP server (sbdk-dev/local-ai-analyst). 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 →