Unlink a scoped control from a custom risk (write — editor+ role). The control and risk both remain; only the mapping is removed.
AI agents call scf_remove_custom_risk_control to permanently remove resources in Scf — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a mapping/link is a deletion operation that cannot be trivially undone — there is no 'restore mapping' implied. While the underlying control and risk records persist, the association between them is permanently severed, making this Destructive. The blast radius is medium because misuse could break compliance mappings and audit trails, but it does not delete core records.
From the tool's definition Unlink a scoped control from a custom risk... only the mapping is removed
Attacks that exploit this kind of access
Unlink a scoped control from a custom risk (write — editor+ role). The control and risk both remain; only the mapping is removed. It is categorised as a Destructive tool in the Scf MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Scf MCP server in PolicyLayer and add a rule for scf_remove_custom_risk_control: 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 Scf. Nothing to install.
scf_remove_custom_risk_control 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 scf_remove_custom_risk_control 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 scf_remove_custom_risk_control. 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.
scf_remove_custom_risk_control is provided by the Scf MCP server (mcp-server-scf). 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 →