删除指定的数据表
AI agents call drop_tables to permanently remove resources in PySqlitMCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool performs irreversible deletion of database tables, which cannot be undone. It matches the Destructive category definition: 'irreversibly deletes or overwrites data, or actions that cannot be undone (delete, drop, purge, force-push)'. The severity is high because dropping tables destroys data at scale with no recovery mechanism, though it is scoped to a specific database rather than system-wide.
From the tool's definition Tool name is 'drop_tables' and description translates to 'delete specified data tables'. The DROP operation in SQL irreversibly removes entire tables and all their data.
Attacks that exploit this kind of access
删除指定的数据表. It is categorised as a Destructive tool in the PySqlitMCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the PySqlit MCP server in PolicyLayer and add a rule for drop_tables: 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 PySqlitMCP. Nothing to install.
drop_tables 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 drop_tables 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 drop_tables. 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.
drop_tables is provided by the PySqlit MCP server (python51888/pysqlitmcp). 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 →