Delete a function from the script project.
AI agents call script_delete_function to permanently remove resources in Gworkspace — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting a function from a script project is an irreversible destructive action that cannot be undone through normal operations. While the blast radius is limited to a single function rather than the entire project, the loss is permanent and could break dependent code or automation workflows. This meets the Destructive category criteria: irreversibly deletes data/code that cannot be undone.
From the tool's definition Tool name is 'script_delete_function' with description 'Delete a function from the script project.' The verb 'delete' indicates irreversible removal of code.
Attacks that exploit this kind of access
Delete a function from the script project. It is categorised as a Destructive tool in the Gworkspace MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Gworkspace MCP server in PolicyLayer and add a rule for script_delete_function: 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 Gworkspace. Nothing to install.
script_delete_function 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 script_delete_function 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 script_delete_function. 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.
script_delete_function is provided by the Gworkspace MCP server (leoonic/gworkspace-mcp). 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 →