AI agents call retry_rate 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 is a statistical/analytic tool that queries and computes metrics from existing data about user search behavior. It has no side effects, does not create or modify records, does not execute code, and does not delete anything. The function is purely observational and informational, consistent with the Read category for retrieval and query operations.
From the tool's definition The tool performs metric calculation and analysis on search behavior ('Reformulation rate per user: searches followed by another search'). It retrieves and aggregates usage statistics with no modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Reformulation rate per user: searches followed by another search within a window with no chunk_fetches in between. 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 retry_rate: 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.
retry_rate 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 retry_rate 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 retry_rate. 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.
retry_rate 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 →