AI agents call rybbit_get_retention to retrieve information from Rybbit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves historical retention metrics and cohort analysis data from Rybbit Analytics. It performs a read-only operation with no side effects on data or external systems. No data is created, modified, deleted, or financial operations are performed. The low severity reflects minimal risk from misuse — an agent cannot damage systems or cause unintended consequences by retrieving analytics reports.
From the tool's definition Tool name contains 'get' and description states 'Get user retention cohort analysis' — retrieves analytics data with no modification, deletion, or execution.
Attacks that exploit this kind of access
Get user retention cohort analysis showing how many users return over time periods. It is categorised as a Read tool in the Rybbit MCP Server, which means it retrieves data without modifying state.
Register the Rybbit MCP server in PolicyLayer and add a rule for rybbit_get_retention: 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 Rybbit. Nothing to install.
rybbit_get_retention 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 rybbit_get_retention 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 rybbit_get_retention. 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.
rybbit_get_retention is provided by the Rybbit MCP server (nks-hub/rybbit-mcp). 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 →