AI agents use ticktick_create_project to create or update resources in Ticktick — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ticktick environment.
This tool creates a new data entity (project/list) in a reversible manner—the created project can subsequently be deleted or modified. This is a Write operation (create), not Destructive, as the action is not irreversible. The severity is low because creating a task management project has minimal blast radius and limited impact to other systems or data integrity.
From the tool's definition Tool creates a new TickTick project/list (irreversible creation of a new entity), as stated in description 'create a new TickTick project/list'.
Attacks that exploit this kind of access
Use this to create a new TickTick project/list. Required: name (1-200 characters). It is categorised as a Write tool in the Ticktick MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ticktick MCP server in PolicyLayer and add a rule for ticktick_create_project: 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 Ticktick. Nothing to install.
ticktick_create_project 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 ticktick_create_project 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 ticktick_create_project. 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.
ticktick_create_project is provided by the Ticktick MCP server (produckteavity/ticktick-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 →