Remove a reference between clawmarks
AI agents call unlink_clawmarks to permanently remove resources in Clawmarks — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a reference between clawmarks is an irreversible deletion of a relationship in the knowledge graph. Unlike soft edits, unlinking destroys the navigational connection between nodes with no indication of an undo mechanism, making it Destructive. Severity is medium because it affects graph structure and context but does not delete the clawmarks themselves.
From the tool's definition 'Remove a reference between clawmarks' — permanently removes an established link/reference between two clawmarks
Attacks that exploit this kind of access
Remove a reference between clawmarks. It is categorised as a Destructive tool in the Clawmarks MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Clawmarks MCP server in PolicyLayer and add a rule for unlink_clawmarks: 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 Clawmarks. Nothing to install.
unlink_clawmarks 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_clawmarks 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_clawmarks. 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_clawmarks is provided by the Clawmarks MCP server (mrilikecoding/clawmarks). 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 →