Creates a new backup vault.
AI agents use create_backup_vault to create or update resources in Observability — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Observability environment.
This tool creates a new backup vault, which is a reversible write operation that establishes a storage container for backup data. While it modifies the cloud infrastructure state, it does not delete data (not Destructive), execute arbitrary code (not Execute), or move money (not Financial).
From the tool's definition Tool name 'create_backup_vault' and description 'Creates a new backup vault' indicate creation of a new resource/configuration in GCP Backup & Disaster Recovery service.
Attacks that exploit this kind of access
Creates a new backup vault. It is categorised as a Write tool in the Observability MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Observability MCP server in PolicyLayer and add a rule for create_backup_vault: 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.
create_backup_vault 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 create_backup_vault 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 create_backup_vault. 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.
create_backup_vault 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.
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 →