AI agents use restore_local_backup 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.
restore_local_backup performs reversible data modification—it restores previously backed-up data to the system. While it has a safe dry-run mode by default, the apply action creates/overwrites task data. This is Write rather than Destructive because restore operations are generally reversible (can be restored again from another backup or undone), and the tool is designed for recovery rather than permanent deletion.
From the tool's definition Tool description states it can "apply a local backup restore" and "write" data, with dry-run as default but actual restoration capability present. The verb "restore" and "apply" indicate data modification.
Attacks that exploit this kind of access
Dry-run or apply a local backup restore. Dry-run is the default and reports conflicts before writing. 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 restore_local_backup: 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.
restore_local_backup 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 restore_local_backup 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 restore_local_backup. 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.
restore_local_backup 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 →