Delete a clawmark
AI agents call delete_clawmark 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.
Deletion of clawmarks (bookmarks documenting code exploration and decision-making) is irreversible. Once deleted, the annotation and the reasoning context it represents cannot be recovered from the system, making this a Destructive action. However, the scope is limited to local JSON file bookmarks rather than critical system data, so severity is medium rather than high or critical.
From the tool's definition Tool name explicitly states 'delete_clawmark' and description confirms 'Delete a clawmark'. The action irreversibly removes bookmarks and their associated metadata from the knowledge graph stored in the local JSON file.
Attacks that exploit this kind of access
Delete a clawmark. 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 delete_clawmark: 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.
delete_clawmark 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_clawmark 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_clawmark. 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_clawmark 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 →