delete_tool
AI agents call delete_tool to permanently remove resources in AutoMCP-SQL — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Delete operations irreversibly remove data and cannot be undone without external backups. This is the most severe category applicable. While the description is empty (lowering confidence slightly from 0.95 to 0.9), the name and context are sufficient to classify with high confidence. An AI agent given access to this tool could permanently destroy database records if misdirected.
From the tool's definition Tool name is 'delete_tool' with empty description. In the context of an auto-generated CRUD interface for SQLite databases, a delete_tool removes records irreversibly from tables.
Attacks that exploit this kind of access
delete_tool. It is categorised as a Destructive tool in the AutoMCP-SQL MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the AutoMCP-SQL MCP server in PolicyLayer and add a rule for delete_tool: 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 AutoMCP-SQL. Nothing to install.
delete_tool 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_tool 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_tool. 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_tool is provided by the AutoMCP-SQL MCP server (mav977/automcp-sql). 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 →