Unified tag management for ClickUp workspaces. SPACE SCOPE - Manage tags in a space: - list: Get all tags in a space - create: Create a new tag (requires tagName, optional colors) - update: Update existing tag (requires tagName, at least one property to update) - delete: Remove tag from space (re...
AI agents call operate_tags to permanently remove resources in ClickUp MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This unified tool includes a 'delete' operation that permanently removes a tag from a space (irreversible, affects all tasks using that tag) and a 'remove' operation that detaches tags from tasks. Because the most severe action available is the space-level delete (which cannot be undone and has broad blast radius across all tasks using that tag), this classifies as Destructive.
From the tool's definition delete: Remove tag from space (requires tagName) — and remove: Remove tag from a task
Attacks that exploit this kind of access
Unified tag management for ClickUp workspaces. SPACE SCOPE - Manage tags in a space: - list: Get all tags in a space - create: Create a new tag (requires tagName, optional colors) - update: Update existing tag (requires tagName, at least one property to update) - delete: Remove tag from space (requires tagName) TASK SCOPE - Manage tag assignments: - add: Add existing tag to a task (tag must exist in space) - remove: Remove tag from a task FLEXIBLE IDENTIFICATION: - Spaces: Use spaceId (preferred) or spaceName - Tasks: Use taskId (preferred), customTaskId (for custom IDs like DEV-1234), or taskName - When using taskName, optionally provide listName to disambiguate COLOR SUPPORT: - Use natural language:. It is categorised as a Destructive tool in the ClickUp MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the ClickUp MCP server in PolicyLayer and add a rule for operate_tags: 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 ClickUp MCP. Nothing to install.
operate_tags 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 operate_tags 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 operate_tags. 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.
operate_tags is provided by the ClickUp MCP server (twofeetup/clickup-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 →