Add tag to task
AI agents use add_tag_to_task to create or update resources in ClickUp MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ClickUp MCP Server environment.
This tool modifies task metadata (tags) in a reversible manner. While it changes state, the operation is not destructive (tags can be removed) and does not delete or overwrite core data. It is not Financial or Execute-level dangerous. The severity is medium because incorrect tag additions across many tasks could create confusion, but the operation is easily reversible through 'remove_tag_from_task' type operations.
From the tool's definition Tool name 'add_tag_to_task' and description 'Add tag to task' indicate a modification operation that creates or appends a tag association to an existing task.
Attacks that exploit this kind of access
Add tag to task. It is categorised as a Write tool in the ClickUp MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the ClickUp MCP Server MCP server in PolicyLayer and add a rule for add_tag_to_task: 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 Server. Nothing to install.
add_tag_to_task is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the add_tag_to_task 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 add_tag_to_task. 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.
add_tag_to_task is provided by the ClickUp MCP Server MCP server (smeric28/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 →