AI agents call stack.report_issue as a supporting operation in Arr Stack workflows.
The tool name suggests reporting an issue, which could be a Write operation (creating a report/ticket), but the description is completely empty. With no description to confirm behavior, and the name alone being ambiguous, confidence is very low. Reporting an issue is typically a low-severity write action, but without evidence I default to Other with low confidence.
From the tool's definition Tool name is 'stack.report_issue'; description is empty and uninformative.
Attacks that exploit this kind of access
stack.report_issue. It is categorised as a Other tool in the Arr Stack MCP Server, which means it performs auxiliary operations.
Register the Arr Stack MCP server in PolicyLayer and add a rule for stack.report_issue: 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 Arr Stack. Nothing to install.
stack.report_issue is a Other tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the stack.report_issue 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 stack.report_issue. 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.
stack.report_issue is provided by the Arr Stack MCP server (new-usemame/arr-stack-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 →