Get project error statistics: received/resolved/unresolved counts for 24h/7d/30d. Quick health check without opening Sentry (~500 tokens saved).
AI agents call sentry_stats to retrieve information from Perceptdot without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool queries and returns aggregated error metrics from Sentry. It has no side effects, creates no data, executes no operations, and performs no destructive actions. This is a straightforward read operation that retrieves monitoring/observability data. Severity is low because misuse would only result in unauthorized visibility into application error metrics, not system compromise or data loss.
From the tool's definition Tool retrieves project error statistics (received/resolved/unresolved counts) for time periods without modifying data. Description explicitly states it performs a 'Quick health check' and saves tokens by avoiding the need to open Sentry directly.
Attacks that exploit this kind of access
Get project error statistics: received/resolved/unresolved counts for 24h/7d/30d. Quick health check without opening Sentry (~500 tokens saved). It is categorised as a Read tool in the Perceptdot MCP Server, which means it retrieves data without modifying state.
Register the Perceptdot MCP server in PolicyLayer and add a rule for sentry_stats: 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 Perceptdot. Nothing to install.
sentry_stats 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 sentry_stats 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 sentry_stats. 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.
sentry_stats is provided by the Perceptdot MCP server (perceptdot/percept). 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 →