AI agents use unarchive_project to create or update resources in Todoist — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Todoist environment.
The tool modifies project state by toggling its archived status. This is a reversible data modification without side effects beyond the project's metadata, placing it in the Write category. Severity is low because unarchiving a project has minimal blast radius—it merely restores visibility/accessibility of an existing project with no cascade effects on tasks or data loss.
From the tool's definition Unarchive a project. This tool reverses the archival state of a project, which is a modification of project metadata. The action is reversible (the project can be re-archived), and it does not delete data or execute arbitrary code.
Attacks that exploit this kind of access
Unarchive a project. It is categorised as a Write tool in the Todoist MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Todoist MCP server in PolicyLayer and add a rule for unarchive_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 Todoist. Nothing to install.
unarchive_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 unarchive_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 unarchive_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.
unarchive_project is provided by the Todoist MCP server (stevengonsalvez/mcp-todoist). 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 →