This record as markdown: /tools/cowork-bench/drop-schemas.md
What drop_schemas does on Cowork Bench
AI agents call drop_schemas to permanently remove resources in Cowork Bench, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why drop_schemas is rated Critical
Dropping database schemas is a destructive operation that cannot be undone and results in permanent loss of data structures and their contents. This represents the most severe category of risk. The action is irreversible and has maximal blast radius if triggered by an AI agent without proper authorization or safeguards.
From the tool's definition Tool name 'drop_schemas' combined with description 'Drop multiple schemas from a database' explicitly indicates irreversible deletion of database schemas and all contained data.
Attacks that exploit this kind of access
The rule that runs drop_schemas safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Cowork Bench, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For drop_schemas, this is the rule to start with:
drop_schemas is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Cowork Bench, apply this rule, and every drop_schemas call is checked against it from then on.
Questions about drop_schemas
Drop multiple schemas from a database. It is categorised as a Destructive tool in the Cowork Bench MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Cowork Bench MCP server in PolicyLayer and add a rule for drop_schemas: 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 Cowork Bench. Nothing to install.
drop_schemas 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_schemas 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_schemas. 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_schemas is provided by the Cowork Bench MCP server (0717376/cowork_bench). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Cowork Bench, and thousands of servers like it.
Across the catalogue