Unsend (retract) a previously sent message.
AI agents call unsend_message to permanently remove resources in Bluebubbles — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Unsending a message is an irreversible action that removes a previously delivered message from the conversation. While some platforms allow a brief window, retracting a message is generally not recoverable by the original sender and permanently removes the message from recipients' view, making it a destructive operation.
From the tool's definition Unsend (retract) a previously sent message
Attacks that exploit this kind of access
Unsend (retract) a previously sent message. It is categorised as a Destructive tool in the Bluebubbles MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Bluebubbles MCP server in PolicyLayer and add a rule for unsend_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 Bluebubbles. Nothing to install.
unsend_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 unsend_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 unsend_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.
unsend_message is provided by the Bluebubbles MCP server (metaember/bluebubbles-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 →