recall_message
AI agents call recall_message to permanently remove resources in Xadeus-QQ-MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
In QQ/messaging platforms, 'recall_message' typically means retracting/deleting a sent message, which is an irreversible destructive action (the message is removed from the chat). The empty description lowers confidence, but the name strongly implies message deletion/retraction. Severity is high because an AI agent could misuse this to silently delete messages from group chats or private conversations.
From the tool's definition Tool name 'recall_message' in a QQ messaging context; description is empty and uninformative.
Attacks that exploit this kind of access
recall_message. It is categorised as a Destructive tool in the Xadeus-QQ-MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Xadeus-QQ- MCP server in PolicyLayer and add a rule for recall_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 Xadeus-QQ-MCP. Nothing to install.
recall_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 recall_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 recall_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.
recall_message is provided by the Xadeus-QQ- MCP server (mouse114514/xadeus-qq-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 →