AI agents use restore_snapshot to create or update resources in Restic — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Restic environment.
The tool restores data from backup snapshots, which involves extracting and writing files to the system. This is a Write operation (reversible, creates/modifies data) rather than Destructive, as restored data can be deleted afterward. However, it has high severity because careless restoration could overwrite important current files or fill storage.
From the tool's definition Tool named 'restore_snapshot' on a restic backup management server; restic restore operations write/extract data from backup snapshots to the filesystem, modifying the target environment. Description is empty, limiting confidence.
Attacks that exploit this kind of access
restore_snapshot. It is categorised as a Write tool in the Restic MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Restic MCP server in PolicyLayer and add a rule for restore_snapshot: 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 Restic. Nothing to install.
restore_snapshot 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_snapshot 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_snapshot. 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_snapshot is provided by the Restic MCP server (mohsenil85/restic-mcp). 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 →