删除bind
AI agents call delete_bind to permanently remove resources in DDNet MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting a bind removes a key binding configuration entry. This is an irreversible action (deletion) rather than a reversible write/update. While the blast radius is moderate (loss of game key bindings that may require manual reconfiguration), it qualifies as Destructive per the classification rules.
From the tool's definition Tool name 'delete_bind' and description '删除bind' (which means 'delete bind' in Chinese) indicate irreversible removal of a key binding configuration.
Attacks that exploit this kind of access
删除bind. It is categorised as a Destructive tool in the DDNet MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the DDNet MCP Server MCP server in PolicyLayer and add a rule for delete_bind: 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 DDNet MCP Server. Nothing to install.
delete_bind 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_bind 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_bind. 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_bind is provided by the DDNet MCP Server MCP server (silverhi/ddnet-mcpserver). 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 →