Delete a dynamic tool and unregister it from MCP
AI agents call dynamic.tool.delete to permanently remove resources in Dynamic — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion of tool definitions is an irreversible action that cannot be undone without recreation. While it does not destroy data stored by applications, it removes tool infrastructure and capabilities from the MCP server state. This is destructive rather than merely Write because the action cannot be reversed through normal update operations.
From the tool's definition Tool name 'dynamic.tool.delete' and description 'Delete a dynamic tool and unregister it from MCP' explicitly indicate irreversible deletion of tool definitions and their MCP registration.
Attacks that exploit this kind of access
Delete a dynamic tool and unregister it from MCP. It is categorised as a Destructive tool in the Dynamic MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Dynamic MCP server in PolicyLayer and add a rule for dynamic.tool.delete: 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 Dynamic. Nothing to install.
dynamic.tool.delete 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 dynamic.tool.delete 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 dynamic.tool.delete. 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.
dynamic.tool.delete is provided by the Dynamic MCP server (mcpland/dynamic-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 →