Remove a specific tag from a job.
AI agents call delete_job_tag to permanently remove resources in CATS MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion operations are inherently irreversible and cannot be undone without manual restoration. While the blast radius is limited to job tag metadata (not the job itself or critical data), this falls clearly into the Destructive category per the classification rules.
From the tool's definition Tool name 'delete_job_tag' explicitly uses the verb 'delete' and description states 'Remove a specific tag from a job.' This irreversibly deletes metadata associated with a job record.
Attacks that exploit this kind of access
Remove a specific tag from a job. It is categorised as a Destructive tool in the CATS MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the CATS MCP Server MCP server in PolicyLayer and add a rule for delete_job_tag: 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 CATS MCP Server. Nothing to install.
delete_job_tag 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_job_tag 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_job_tag. 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_job_tag is provided by the CATS MCP Server MCP server (vanman2024/cats-mcp-server). 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 →