startAutomation · OpenAI Web Search MCP Server MCP

WHAT IT DOES

What startAutomation does on OpenAI Web Search MCP Server

AI agents invoke startAutomation to trigger actions in OpenAI Web Search MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why startAutomation needs a policy

This tool executes a pre-defined automation workflow whose effects depend on what the saved automation contains. While the automation itself is defined elsewhere, triggering it ('initiates a new flow run') qualifies as Execute because the tool causes external operations to occur.

From the tool's definition The tool 'startAutomation' initiates a new flow run for a specific saved automation. The verb 'initiates' combined with 'flow run' indicates execution of external operations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

startAutomation Rate-limited

startAutomation stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "startAutomation": {
      "limits": [
        {
          "counter": "startautomation_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches OpenAI Web Search MCP Server, so you can run agents against it safely.

FAQ

Questions about startAutomation

What does the startAutomation tool do? +

Initiates a new flow run for a specific saved automation. It is categorised as a Execute tool in the OpenAI Web Search MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on startAutomation? +

Register the OpenAI Web Search MCP Server MCP server in PolicyLayer and add a rule for startAutomation: 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 OpenAI Web Search MCP Server. Nothing to install.

What risk level is startAutomation? +

startAutomation is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit startAutomation? +

Yes. Add a rate_limit block to the startAutomation 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 startAutomation completely? +

Set action: deny in the PolicyLayer policy for startAutomation. 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 startAutomation? +

startAutomation is provided by the OpenAI Web Search MCP Server MCP server (tiovikram/gumloop-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.