AI agents use create_incident to create or update resources in Rootly — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Rootly environment.
The tool creates new incident records, which is a reversible write operation. While incidents are important for incident response workflows, creating them does not destroy data, execute arbitrary code, or move money. However, severity is elevated (high) because a malicious agent could flood the system with false incidents, disrupting incident response operations and causing organizational disruption.
From the tool's definition Tool named 'create_incident' with empty description. Sibling tools indicate this is a Rootly incident management server. Creating incidents is a write operation that generates new records in the incident tracking system.
Documented attack patterns abuse exactly the kind of access create_incident gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Rootly, and nothing reaches the server without passing your rules. This is the rule we recommend for create_incident:
{
"version": "1",
"default": "deny",
"tools": {
"create_incident": {
"limits": [
{
"counter": "create_incident_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_incident stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
create_incident. It is categorised as a Write tool in the Rootly MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Rootly MCP server in PolicyLayer and add a rule for create_incident: 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 Rootly. Nothing to install.
create_incident 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_incident 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_incident. 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_incident is provided by the Rootly MCP server (https://mcp.rootly.com/sse). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Rootly, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
20 Rootly tools catalogued and risk-classified — across an index of 43,000+ MCP servers.