AI agents use machines_unarchive 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.
Unarchiving is a write operation that modifies data (changes machine status) but is reversible by re-archiving. It does not delete data, execute code, move money, or cause irreversible damage. The medium severity reflects that restoring an archived machine could have operational impacts if done incorrectly by an agent, but the action itself is not destructive or high-risk.
From the tool's definition Tool name 'machines_unarchive' and description 'Unarchive a machine' indicate a reversal of archival status—modifying the state of a machine record from archived to active.
Attacks that exploit this kind of access
Unarchive a machine. 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 machines_unarchive: 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.
machines_unarchive 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 machines_unarchive 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 machines_unarchive. 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.
machines_unarchive 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 →