Get unresolved Sentry issues sorted by priority. Replaces manual Sentry dashboard browsing (~500 tokens saved, zero human interruption). Returns structured JSON with id, title, level, counts.
AI agents call sentry_issues 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 is a pure data retrieval mechanism—it fetches error/issue data from Sentry and presents it in structured form. The action is read-only with no side effects. While Sentry data can be sensitive (error traces may contain application internals), the tool itself performs no destructive, financial, or execute-type actions.
From the tool's definition Tool retrieves and queries unresolved Sentry issues, returning structured JSON data. Description explicitly states it 'replaces manual Sentry dashboard browsing' and 'returns structured JSON with id, title, level, counts'.
Attacks that exploit this kind of access
Get unresolved Sentry issues sorted by priority. Replaces manual Sentry dashboard browsing (~500 tokens saved, zero human interruption). Returns structured JSON with id, title, level, counts. 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_issues: 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_issues 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_issues 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_issues. 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_issues 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 →