Delete an ADR (moves to trash)
AI agents call delete_adr to permanently remove resources in Planning Game — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly removes data (Architecture Decision Records) from the system. Although it moves items to trash rather than permanently purging them, it constitutes a destructive action that removes data from normal access and cannot be easily recovered by an AI agent without administrative intervention.
From the tool's definition Tool name is 'delete_adr' and description states 'Delete an ADR (moves to trash)' - explicitly performs deletion of Architecture Decision Records.
Attacks that exploit this kind of access
Delete an ADR (moves to trash). It is categorised as a Destructive tool in the Planning Game MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Planning Game MCP server in PolicyLayer and add a rule for delete_adr: 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 Planning Game. Nothing to install.
delete_adr 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 delete_adr 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 delete_adr. 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.
delete_adr is provided by the Planning Game MCP server (planning-game-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 →