submit_demo
Synthetic irreversible action; ARL must block it in SAFE_LIVE.
This record as markdown: /tools/agent-reliability-lab/submit-demo.md
What submit_demo does on Agent Reliability Lab
AI agents call submit_demo to permanently remove resources in Agent Reliability Lab, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why submit_demo is rated Critical
An AI agent that decides to call submit_demo doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from Agent Reliability Lab is gone. There is no undo for destructive operations.
Attacks that exploit this kind of access
The rule that runs submit_demo safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Agent Reliability Lab, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For submit_demo, this is the rule to start with:
submit_demo is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Agent Reliability Lab, apply this rule, and every submit_demo call is checked against it from then on.
Questions about submit_demo
Synthetic irreversible action; ARL must block it in SAFE_LIVE. It is categorised as a Destructive tool in the Agent Reliability Lab MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Agent Reliability Lab MCP server in PolicyLayer and add a rule for submit_demo: 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 Agent Reliability Lab. Nothing to install.
submit_demo is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the submit_demo 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 submit_demo. 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.
submit_demo is provided by the Agent Reliability Lab MCP server (Andrem19/agent-reliability-lab). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Agent Reliability Lab, and thousands of servers like it.
Across the catalogue