Fetch recent issues from Sentry for investigation
AI agents call get_sentry_issues to retrieve information from Sentry Investigator without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves Sentry issue data for analysis. It has no side effects—it queries an existing data source without creating, modifying, deleting, or executing anything. This is a straightforward read operation with minimal blast radius if misused (potential information disclosure of issue details, but no system state changes).
From the tool's definition Tool name and description indicate fetching/retrieving data: 'Fetch recent issues from Sentry for investigation.' No modification, deletion, or execution of external operations occurs.
Attacks that exploit this kind of access
Fetch recent issues from Sentry for investigation. It is categorised as a Read tool in the Sentry Investigator MCP Server, which means it retrieves data without modifying state.
Register the Sentry Investigator MCP server in PolicyLayer and add a rule for get_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 Sentry Investigator. Nothing to install.
get_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 get_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 get_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.
get_sentry_issues is provided by the Sentry Investigator MCP server (vibe-code-agent/sentry-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 →