AI agents use add_task_update to create or update resources in Dooist — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Dooist environment.
The tool adds updates to task records, which is a create operation on task metadata. This is reversible (updates can be edited or removed) and has no destructive or executable side effects. It falls squarely into Write category rather than Read (it modifies data) or Execute (it doesn't run code or external commands).
From the tool's definition Tool description states 'Add a timestamped status update to a task', which creates new data (status updates) reversibly. This is a write operation that modifies task state without deletion or code execution.
Attacks that exploit this kind of access
Add a timestamped status update to a task. Use this to track progress and activity on a task over time. It is categorised as a Write tool in the Dooist MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Dooist MCP server in PolicyLayer and add a rule for add_task_update: 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 Dooist. Nothing to install.
add_task_update 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_update 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_update. 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_update is provided by the Dooist MCP server (papermoose/dooist). 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 →