clickup_action · UnClick MCP: Risk & Policy

WHAT IT DOES

What clickup_action does on UnClick

AI agents use clickup_action to create or update resources in UnClick — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your UnClick environment.

PARAMETERS

Parameter	Type	Required	Description
`name`	string	—	Task name (for create_task and update_task).
`page`	number	—	Page number for task pagination.
`action`	string	Yes	Action: get_workspaces, get_spaces, get_lists, get_tasks, create_task, update_task.
`status`	string	—	Task status name.
`api_key`	string	Yes	ClickUp API key.
`list_id`	string	—	List ID (for get_tasks and create_task).
`task_id`	string	—	Task ID (for update_task).
`team_id`	string	—	Workspace (team) ID (for get_spaces).
`due_date`	number	—	Due date as Unix timestamp in milliseconds.
`priority`	number	—	Priority: 1 (urgent), 2 (high), 3 (normal), 4 (low).
`space_id`	string	—	Space ID (for get_lists without a folder).
`folder_id`	string	—	Folder ID (for get_lists).

Parameters from the server's own tool schema.

WHY IT NEEDS A POLICY

Why clickup_action needs a policy

The tool performs both Read operations (list, get) and Write operations (create, update). Per classification rules, Write is more severe than Read, so it maps to the Write category. The blast radius is medium because an agent could create spurious tasks or modify task state in ClickUp workspaces, but these are reversible actions. No destructive deletion, financial, or code execution capability is mentioned.

From the tool's definition Tool description explicitly states 'create tasks, and update task properties' — reversible data modifications. Also lists read capabilities ('list workspaces and spaces, get lists and tasks') but creation and update are the most severe capabilities present.

Risk signalsHandles credentials or secrets (api_key) · High parameter count (13 properties)

Attacks that exploit this kind of access

Questions about clickup_action

What does the clickup_action tool do? +

Interact with the ClickUp API v2: list workspaces and spaces, get lists and tasks, create tasks, and update task properties. It is categorised as a Write tool in the UnClick MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does clickup_action accept? +

clickup_action accepts 12 parameters: name, page, action, status, api_key, list_id, task_id, team_id, due_date, priority, space_id, folder_id. Required: action, api_key. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on clickup_action? +

Register the UnClick MCP server in PolicyLayer and add a rule for clickup_action: 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 UnClick. Nothing to install.

What risk level is clickup_action? +

clickup_action is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit clickup_action? +

Yes. Add a rate_limit block to the clickup_action 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.

How do I block clickup_action completely? +

Set action: deny in the PolicyLayer policy for clickup_action. 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.

What MCP server provides clickup_action? +

clickup_action is provided by the UnClick MCP server (@unclick/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.