AI agents call diff_snapshots to retrieve information from Restic without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The diff_snapshots tool performs a comparison operation between two existing snapshots. This is fundamentally a data retrieval and analysis task with no side effects—it does not create, modify, delete, or execute any operations. While it operates on backups (which are critical infrastructure), the tool itself only reads and displays differences. No destructive, financial, or execution capabilities are involved.
From the tool's definition Tool name 'diff_snapshots' and description 'Show differences between two backup snapshots' indicate a read-only operation that retrieves and compares metadata/content between snapshots without modifying or deleting any data.
Attacks that exploit this kind of access
Show differences between two backup snapshots. It is categorised as a Read tool in the Restic MCP Server, which means it retrieves data without modifying state.
Register the Restic MCP server in PolicyLayer and add a rule for diff_snapshots: 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.
diff_snapshots is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the diff_snapshots 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 diff_snapshots. 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.
diff_snapshots 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 →