custom_instructions_set · Openai MCP: Risk & Policy

WHAT IT DOES

What custom_instructions_set does on Openai

AI agents use custom_instructions_set to create or update resources in Openai — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Openai environment.

WHY IT NEEDS A POLICY

Why custom_instructions_set needs a policy

This tool creates or modifies user account settings (custom instructions for ChatGPT) in a reversible manner. It does not delete data permanently (Destructive), execute arbitrary code (Execute), move money (Financial), or retrieve data without side effects (Read).

From the tool's definition Tool description states 'Overwrite ChatGPT custom instructions' which modifies user account settings. The read-modify-write pattern indicates reversible modification of stored configuration data.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

custom_instructions_set Rate-limited

custom_instructions_set 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "custom_instructions_set": {
      "limits": [
        {
          "counter": "custom_instructions_set_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

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 custom_instructions_set

What does the custom_instructions_set tool do? +

Overwrite ChatGPT custom instructions (read-modify-write — preserves fields not supplied). It is categorised as a Write tool in the Openai MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on custom_instructions_set? +

Register the Openai MCP server in PolicyLayer and add a rule for custom_instructions_set: 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 custom_instructions_set? +

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

Can I rate-limit custom_instructions_set? +

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

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

custom_instructions_set 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.