Add a dependency between tasks
AI agents use add-task-dependency to create or update resources in ClickUp Operator — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ClickUp Operator environment.
This tool creates or modifies task metadata (dependencies) reversibly without deleting data or executing arbitrary code. It falls under Write category as it establishes a new relationship/link between entities. Severity is medium because misuse could create circular dependencies or incorrect task hierarchies that disrupt project planning, but this is reversible through removing the dependency.
From the tool's definition Tool description states 'Add a dependency between tasks' which modifies the relationship structure between tasks in ClickUp, creating a new dependency link that did not exist before.
Attacks that exploit this kind of access
Add a dependency between tasks. It is categorised as a Write tool in the ClickUp Operator MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the ClickUp Operator MCP server in PolicyLayer and add a rule for add-task-dependency: 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 Operator. Nothing to install.
add-task-dependency 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-task-dependency 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-task-dependency. 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-task-dependency is provided by the ClickUp Operator MCP server (noah-vh/mcp-server-clickup). 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 →