AI agents use unarchive_task to create or update resources in Todos — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Todos environment.
This tool modifies task metadata reversibly by changing a task's status/state from archived back to pending. This is a Write operation because it creates or modifies data reversibly without destructive or financial consequences. Severity is medium because an agent misusing this could restore many archived tasks unintentionally, cluttering the task system, but changes are reversible (the task can be re-archived).
From the tool's definition Tool name 'unarchive_task' and description 'Restore an archived task back to pending' indicate modification of task state from archived to pending status.
Attacks that exploit this kind of access
Restore an archived task back to pending. It is categorised as a Write tool in the Todos MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Todos MCP server in PolicyLayer and add a rule for unarchive_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 Todos. Nothing to install.
unarchive_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 unarchive_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 unarchive_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.
unarchive_task is provided by the Todos MCP server (@hasna/todos). 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 →