Get sample queries for a specific model to help users get started.
AI agents call get_sample_queries 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.
This tool retrieves example or template queries from a model's metadata to assist users in understanding available query patterns. It performs no data modification, code execution, deletion, or financial operations. It is purely informational and has no side effects beyond returning read-only reference material.
From the tool's definition Tool description states 'Get sample queries for a specific model' - a retrieval operation with no modification of data or execution of operations. The verb 'get' and the purpose of helping users understand available queries indicate read-only functionality.
Attacks that exploit this kind of access
Get sample queries for a specific model to help users get started. 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 get_sample_queries: 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.
get_sample_queries 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 get_sample_queries 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 get_sample_queries. 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.
get_sample_queries 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 →