trigger_backup · Observability MCP: Risk & Policy

WHAT IT DOES

What trigger_backup does on Observability

AI agents invoke trigger_backup to trigger actions in Observability. 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.

WHY IT NEEDS A POLICY

Why trigger_backup needs a policy

This tool executes a backup operation, which is a system action with side effects that depends on runtime arguments (the backup plan association). It is not a simple read (no data retrieval), not write in the reversible sense (backups are typically managed operations), and not destructive by itself. It does trigger an external process, making it Execute category.

From the tool's definition Tool name 'trigger_backup' and description 'Triggers a backup for a given backup plan association' indicate an action that initiates an external operation (backup process) whose effects depend on the backup plan association specified.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

trigger_backup Rate-limited

trigger_backup stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "trigger_backup": {
      "limits": [
        {
          "counter": "trigger_backup_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Observability, so you can run agents against it safely.

FAQ

Questions about trigger_backup

What does the trigger_backup tool do? +

Triggers a backup for a given backup plan association. It is categorised as a Execute tool in the Observability MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on trigger_backup? +

Register the Observability MCP server in PolicyLayer and add a rule for trigger_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 Observability. Nothing to install.

What risk level is trigger_backup? +

trigger_backup is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit trigger_backup? +

Yes. Add a rate_limit block to the trigger_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.

How do I block trigger_backup completely? +

Set action: deny in the PolicyLayer policy for trigger_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.

What MCP server provides trigger_backup? +

trigger_backup is provided by the Observability MCP server (@google-cloud/observability-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.