Medium Risk

create_override_recommendation

create_override_recommendation

How to control create_override_recommendation ↓

What create_override_recommendation does on Rootly

AI agents use create_override_recommendation 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.

Medium Risk

Why create_override_recommendation needs a policy

This tool creates or modifies a recommendation, which is reversible (can be updated or deleted). Given the incident management context (sibling tools include create_incident, get_incident, etc.), this likely creates or updates override recommendations for on-call schedules or incident handling. Without explicit description, confidence is moderate.

From the tool's definition Tool name 'create_override_recommendation' indicates creation of a new recommendation object that overrides existing guidance or policy. The verb 'create' signals data modification.

Documented attack patterns abuse exactly the kind of access create_override_recommendation gives an agent:

How to control create_override_recommendation

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_override_recommendation:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_override_recommendation": {
      "limits": [
        {
          "counter": "create_override_recommendation_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

create_override_recommendation 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.

  1. Create a free account and register Rootly — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about create_override_recommendation

What does the create_override_recommendation tool do? +

create_override_recommendation. 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.

How do I enforce a policy on create_override_recommendation? +

Register the Rootly MCP server in PolicyLayer and add a rule for create_override_recommendation: 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.

What risk level is create_override_recommendation? +

create_override_recommendation is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit create_override_recommendation? +

Yes. Add a rate_limit block to the create_override_recommendation 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.

How do I block create_override_recommendation completely? +

Set action: deny in the PolicyLayer policy for create_override_recommendation. 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.

What MCP server provides create_override_recommendation? +

create_override_recommendation 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.

Enforce policy on every Rootly tool call.

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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.