AI agents call top_queries to retrieve information from Paparats without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and aggregates historical query statistics from the semantic code search system. It performs data retrieval and analysis only, with no side effects, data modification, or external action triggers. The read-only nature and benign informational output (frequency counts, latencies, result statistics) present minimal risk if misused by an AI agent.
From the tool's definition Tool returns aggregate metrics about queries: 'Most-frequent queries by query_hash with one example, count, avg latency, avg result count.' No modification, deletion, or execution of external operations occurs.
Attacks that exploit this kind of access
Most-frequent queries by query_hash with one example, count, avg latency, avg result count. It is categorised as a Read tool in the Paparats MCP Server, which means it retrieves data without modifying state.
Register the Paparats MCP server in PolicyLayer and add a rule for top_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 Paparats. Nothing to install.
top_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 top_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 top_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.
top_queries is provided by the Paparats MCP server (@paparats/cli). 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 →