deep_research · Openai MCP: Risk & Policy

WHAT IT DOES

What deep_research does on Openai

AI agents invoke deep_research to trigger actions in Openai. 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 deep_research needs a policy

The description is empty, lowering confidence. Based on the server description referencing 'deep research' and the sibling tool 'deep_research_heavy', this tool likely triggers an external research operation (querying multiple sources, running an AI research agent). This constitutes an Execute action as it triggers external operations.

From the tool's definition Tool name 'deep_research' and server description mentions 'deep research' as a capability that triggers external operations via ChatGPT account

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

deep_research Rate-limited

deep_research 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": {
    "deep_research": {
      "limits": [
        {
          "counter": "deep_research_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, so you can run agents against it safely.

FAQ

Questions about deep_research

What does the deep_research tool do? +

deep_research. It is categorised as a Execute tool in the Openai MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on deep_research? +

Register the Openai MCP server in PolicyLayer and add a rule for deep_research: 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. Nothing to install.

What risk level is deep_research? +

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

Can I rate-limit deep_research? +

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

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

deep_research is provided by the Openai MCP server (robotlearning123/gpt2agent). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.