AI agents call collect_incidents to retrieve information from Rootly without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool is most likely a retrieval/aggregation operation that gathers incident information from the Rootly incident management platform. No modification, deletion, or external action is implied by the name.
From the tool's definition Tool name 'collect_incidents' follows the pattern of sibling tools like 'get_incident', 'find_related_incidents', and 'check_oncall_health_risk', which are all query/retrieval operations.
Documented attack patterns abuse exactly the kind of access collect_incidents 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 collect_incidents:
{
"version": "1",
"default": "deny",
"tools": {
"collect_incidents": {}
}
}collect_incidents is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
collect_incidents. It is categorised as a Read tool in the Rootly MCP Server, which means it retrieves data without modifying state.
Register the Rootly MCP server in PolicyLayer and add a rule for collect_incidents: 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.
collect_incidents is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the collect_incidents 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 collect_incidents. 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.
collect_incidents 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.