Delete a message
AI agents call delete_message to permanently remove resources in Follow Plan MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes data (a message) from the system. Deletion is an irreversible operation with no undo capability. While the blast radius is somewhat contained (single message vs. database wipe), the destructive nature of the action places it in the Destructive category, which takes precedence over Write.
From the tool's definition Tool name is 'delete_message' with description 'Delete a message'. The verb 'delete' is explicitly destructive and irreversible.
Attacks that exploit this kind of access
Delete a message. It is categorised as a Destructive tool in the Follow Plan MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Follow Plan MCP Server MCP server in PolicyLayer and add a rule for delete_message: 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 Follow Plan MCP Server. Nothing to install.
delete_message 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_message 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_message. 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_message is provided by the Follow Plan MCP Server MCP server (vibeclasses/follow-plan-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 →