AI agents call stack.dryrun_log to retrieve information from Arr Stack without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The name 'dryrun_log' implies accessing historical or simulated execution logs for review purposes. A dry-run typically does not have persistent side effects, and accessing logs is a read-like operation. However, confidence is moderate (0.6) due to the empty description leaving room for interpretation about whether this might trigger any external operations or side effects.
From the tool's definition Tool name 'dryrun_log' suggests retrieving or querying log output from a dry-run simulation, with no indication of data modification or destruction.
Attacks that exploit this kind of access
stack.dryrun_log. It is categorised as a Read tool in the Arr Stack MCP Server, which means it retrieves data without modifying state.
Register the Arr Stack MCP server in PolicyLayer and add a rule for stack.dryrun_log: 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.dryrun_log 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 stack.dryrun_log 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.dryrun_log. 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.dryrun_log 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 →