Deletes a decision by its ID.
AI agents call delete_decision_by_id to permanently remove resources in SDOF Knowledge Base — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes decision records from the knowledge base without the ability to undo the operation. While the blast radius is limited to decision records (not system-critical), deletion is irreversible and constitutes a destructive operation. Severity is high rather than critical because the impact is scoped to individual decision records rather than the entire system or financial data.
From the tool's definition Tool name explicitly contains "delete" and description states "Deletes a decision by its ID." The action is irreversible deletion of data.
Attacks that exploit this kind of access
Deletes a decision by its ID. It is categorised as a Destructive tool in the SDOF Knowledge Base MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the SDOF Knowledge Base MCP server in PolicyLayer and add a rule for delete_decision_by_id: 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 SDOF Knowledge Base. Nothing to install.
delete_decision_by_id 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_decision_by_id 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_decision_by_id. 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_decision_by_id is provided by the SDOF Knowledge Base MCP server (tgf-between-your-legs/sdof-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 →