AI agents use backup_database 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 creates a new backup artifact (Write category) rather than executing code, deleting data, or modifying existing task records. The backup operation is reversible and non-destructive. Severity is low because creating backups has minimal blast radius—it only adds a new file without affecting running tasks or system state. The confidence is high as the description clearly indicates file creation via backup.
From the tool's definition Tool creates a local atomic backup of the todos SQLite database. The verb 'backup' and the action of creating a backup file indicates data is being written/created, not deleted or executed.
Attacks that exploit this kind of access
Create a local atomic backup of the todos SQLite database. 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 backup_database: 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.
backup_database 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 backup_database 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 backup_database. 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.
backup_database 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 →