Get search queries that AI models generated when answering prompts. Returns the actual search queries models used to find information. Useful for understanding how AI models research topics. Without date filters, returns data across all available dates. Empty results may indicate the project has ...
AI agents call search_queries to retrieve information from Peecai without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical search query data generated by AI models. It performs a read-only query operation with optional filtering by date and other parameters. While it may expose information about how AI models research topics, this is a passive retrieval with no capability to modify, delete, or execute actions.
From the tool's definition Tool description states 'Get search queries' and 'Returns the actual search queries' - uses retrieval language (get, returns) with no modification or deletion operations. No side effects or data mutation.
Attacks that exploit this kind of access
Get search queries that AI models generated when answering prompts. Returns the actual search queries models used to find information. Useful for understanding how AI models research topics. Without date filters, returns data across all available dates. Empty results may indicate the project has no query data for the given time range or filters. It is categorised as a Read tool in the Peecai MCP Server, which means it retrieves data without modifying state.
Register the Peecai MCP server in PolicyLayer and add a rule for search_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 Peecai. Nothing to install.
search_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 search_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 search_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.
search_queries is provided by the Peecai MCP server (mcp-server-peecai). 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 →