delete_key
AI agents call delete_key to permanently remove resources in Ast Editor — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Although the description is empty (lowering confidence slightly), the tool name 'delete_key' combined with sibling tools like 'delete_symbol' and 'delete_in_body' establishes a clear destructive pattern on this server. Deleting keys from code structures (e.g., object properties, map entries, configuration fields) is irreversible.
From the tool's definition Tool name is 'delete_key' with empty description. Server description indicates 'surgical tools for structural edits' including 'delete_symbol' (a sibling tool).
Attacks that exploit this kind of access
delete_key. It is categorised as a Destructive tool in the Ast Editor MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Ast Editor MCP server in PolicyLayer and add a rule for delete_key: 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 Ast Editor. Nothing to install.
delete_key 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_key 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_key. 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_key is provided by the Ast Editor MCP server (kambleakash0/ast-editor). 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 →