Remove a dependency edge by id.
AI agents call unlink_intentions to permanently remove resources in Planning System MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
An AI agent that decides to call unlink_intentions doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from Planning System MCP Server is gone — there is no undo for destructive operations.
Attacks that exploit this kind of access
Remove a dependency edge by id. It is categorised as a Destructive tool in the Planning System MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Planning System MCP Server MCP server in PolicyLayer and add a rule for unlink_intentions: 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 System MCP Server. Nothing to install.
unlink_intentions 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 unlink_intentions 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 unlink_intentions. 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.
unlink_intentions is provided by the Planning System MCP Server MCP server (tagents/agent-planner-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.