Delete a reference
AI agents call delete_ref to permanently remove resources in Substrate — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool performs an irreversible deletion operation on references within the Substrate foundation. Deletion cannot be undone without external backup/recovery mechanisms, making it destructive. High severity is appropriate because deleted references could represent important system state, configurations, or documentation links.
From the tool's definition Tool name is 'delete_ref' with description 'Delete a reference'. The verb 'delete' indicates irreversible removal of data.
Attacks that exploit this kind of access
Delete a reference. It is categorised as a Destructive tool in the Substrate MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Substrate MCP server in PolicyLayer and add a rule for delete_ref: 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 Substrate. Nothing to install.
delete_ref 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_ref 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_ref. 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_ref is provided by the Substrate MCP server (ivan-saorin/substrate). 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 →