Legt einen neuen Monitor an. type: http (HTTP-GET auf URL) /
AI agents use uptime_add_monitor to create or update resources in Uptime Kuma — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Uptime Kuma environment.
Creating a new monitor is a write operation that modifies the monitoring system's state by adding a new tracked resource. It is reversible (can be deleted via uptime_delete_monitor), so it does not qualify as Destructive.
From the tool's definition Tool description states 'Legt einen neuen Monitor an' (Creates a new monitor). The sibling tool 'uptime_delete_monitor' confirms this server handles monitor lifecycle management. This is a create operation that adds a new monitoring configuration.
Attacks that exploit this kind of access
Legt einen neuen Monitor an. type: http (HTTP-GET auf URL) /. It is categorised as a Write tool in the Uptime Kuma MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Uptime Kuma MCP server in PolicyLayer and add a rule for uptime_add_monitor: 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 Uptime Kuma. Nothing to install.
uptime_add_monitor 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 uptime_add_monitor 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 uptime_add_monitor. 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.
uptime_add_monitor is provided by the Uptime Kuma MCP server (mbay-odw/uptime-kuma-mcp-server). 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 →