Delete a direct message by its ID.
AI agents call delete_dm to permanently remove resources in MCP-Twikit — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes a direct message, which is an irreversible action. Even though it operates on a single message (not mass deletion), deletion is categorized as Destructive per the classification rules. The severity is high because an AI agent could maliciously delete important communications between users, and the blast radius includes loss of message history and potential privacy/trust damage.
From the tool's definition Tool name 'delete_dm' combined with description 'Delete a direct message by its ID' explicitly performs an irreversible deletion operation. The verb 'delete' and action of removing a direct message indicate data cannot be recovered.
Attacks that exploit this kind of access
Delete a direct message by its ID. It is categorised as a Destructive tool in the MCP-Twikit MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP-Twikit MCP server in PolicyLayer and add a rule for delete_dm: 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 MCP-Twikit. Nothing to install.
delete_dm 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_dm 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_dm. 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_dm is provided by the MCP-Twikit MCP server (zo-valentine/mcp-twikit). 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 →