AI agents invoke backup_restore_test to trigger actions in Infra Ops. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes a restore operation (extracting backup contents to a temporary location), which is an active operation with side effects on the filesystem. It is not purely read-only since it writes extracted data to disk. However, since it targets a temporary location and is framed as a test/verification step rather than a production restore, it is not inherently destructive.
From the tool's definition 'Test restoring a backup by extracting to a temporary location and verifying contents' — performs an active extraction/restore operation to a filesystem location
Attacks that exploit this kind of access
Test restoring a backup by extracting to a temporary location and verifying contents. It is categorised as a Execute tool in the Infra Ops MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Infra Ops MCP server in PolicyLayer and add a rule for backup_restore_test: 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 Infra Ops. Nothing to install.
backup_restore_test is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the backup_restore_test 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_restore_test. 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_restore_test is provided by the Infra Ops MCP server (skyvanguard/infra-ops-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 →