Add a URL check to an existing StillOnline project. Use this for additional SaaS endpoints, API health URLs, MCP backends, or autonomous agent health checks.
AI agents use checks.create to create or update resources in Stillonline — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Stillonline environment.
This tool creates new monitoring checks within a project, which is a Write operation (creates data reversibly). While it doesn't modify existing checks or delete them, it does establish new monitoring rules that will affect system behavior. Severity is medium because misuse could lead to performance impact from excessive checks or monitoring of unintended URLs, but the effect is reversible via checks.delete.
From the tool's definition The tool performs 'Add a URL check' operation which creates new monitoring configuration. The description states it adds checks to a project, which is a reversible data creation action.
Attacks that exploit this kind of access
Add a URL check to an existing StillOnline project. Use this for additional SaaS endpoints, API health URLs, MCP backends, or autonomous agent health checks. It is categorised as a Write tool in the Stillonline MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Stillonline MCP server in PolicyLayer and add a rule for checks.create: 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 Stillonline. Nothing to install.
checks.create 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 checks.create 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 checks.create. 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.
checks.create is provided by the Stillonline MCP server (shenwell/stillonline-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 →