Soft-delete the link between an AnchorID and a source record.
AI agents call unlink_source_record to permanently remove resources in Anchord MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Even though it is a 'soft-delete', the action removes/severs the link between an AnchorID and a source record. This is a deletion operation that breaks the canonical identity resolution chain. While potentially reversible at the data layer, it is described as a delete and its misuse could disrupt identity resolution across customer systems at scale, warranting a Destructive classification with high severity.
From the tool's definition Soft-delete the link between an AnchorID and a source record
Attacks that exploit this kind of access
Soft-delete the link between an AnchorID and a source record. It is categorised as a Destructive tool in the Anchord MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Anchord MCP server in PolicyLayer and add a rule for unlink_source_record: 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 Anchord MCP. Nothing to install.
unlink_source_record 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 unlink_source_record 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 unlink_source_record. 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.
unlink_source_record is provided by the Anchord MCP server (nolenation04/anchord-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 →