Deletes a specific custom data entry.
AI agents call delete_custom_data 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 directly removes data without apparent undo capability. Deletion is an irreversible operation that destroys information. Given the context of a knowledge base managing 'persistent memory and context,' removing custom data entries could disrupt AI system decision-making, lose learned patterns, or erase critical contextual information.
From the tool's definition Tool name is 'delete_custom_data' which explicitly performs deletion. Description states it 'Deletes a specific custom data entry.' The verb 'delete' combined with lack of any mention of reversibility or soft-delete indicates irreversible removal of data.
Attacks that exploit this kind of access
Deletes a specific custom data entry. 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_custom_data: 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_custom_data 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_custom_data 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_custom_data. 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_custom_data 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 →