AI agents call remove_tag to permanently remove resources in Kanban — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool name 'remove_tag' strongly implies removing/deleting a tag association, which is a destructive (irreversible) operation. The description is empty, so confidence is reduced, but the naming pattern and sibling tools (delete_tag, delete_item, delete_decision) confirm a destructive pattern. Severity is medium since tags are metadata and the underlying item is not deleted.
From the tool's definition Tool name 'remove_tag' on a server with sibling tools 'add_tag', 'delete_tag', 'delete_item', 'delete_decision' — removal/deletion pattern is consistent across the server
Documented attack patterns abuse exactly the kind of access remove_tag gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Kanban, and nothing reaches the server without passing your rules. This is the rule we recommend for remove_tag:
{
"version": "1",
"default": "deny",
"hide": [
"remove_tag"
]
}remove_tag disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
remove_tag. It is categorised as a Destructive tool in the Kanban MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Kanban MCP server in PolicyLayer and add a rule for remove_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 Kanban. Nothing to install.
remove_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 remove_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 remove_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.
remove_tag is provided by the Kanban MCP server (multidimensionalcats/kanban-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Kanban, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
45 Kanban tools catalogued and risk-classified — across an index of 43,000+ MCP servers.