AI agents use ops_create_maintenance to create or update resources in Ops — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ops environment.
This tool creates maintenance records which are reversible changes to Statuspage state. It does not execute arbitrary operations (Execute), destroy data irreversibly (Destructive), or move money (Financial). The severity is medium because creating false or disruptive maintenance windows could mislead stakeholders and impact business operations, but the effect is correctable.
From the tool's definition Tool description states 'Create scheduled maintenance on Statuspage' — creates new maintenance events that modify service status information.
Attacks that exploit this kind of access
Create scheduled maintenance on Statuspage. It is categorised as a Write tool in the Ops MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ops MCP server in PolicyLayer and add a rule for ops_create_maintenance: 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 Ops. Nothing to install.
ops_create_maintenance 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 ops_create_maintenance 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 ops_create_maintenance. 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.
ops_create_maintenance is provided by the Ops MCP server (sydney-robotics-academy/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 →