Updates a backup plan.
AI agents use update_backup_plan 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.
Modifying a backup plan is a Write operation—it creates or modifies data reversibly without permanently destroying resources. However, severity is high because incorrect backup plan updates could compromise data recovery capabilities, affecting critical infrastructure. The blast radius includes potential loss of recovery options for important systems if the plan is misconfigured.
From the tool's definition Tool name: 'update_backup_plan'; description: 'Updates a backup plan.' The verb 'Updates' indicates modification of existing data (backup plan configuration). This is a write operation that changes backup settings reversibly.
Attacks that exploit this kind of access
Updates a backup plan. 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 update_backup_plan: 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.
update_backup_plan 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 update_backup_plan 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 update_backup_plan. 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.
update_backup_plan 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 →