// SCAN REPORT

ChatGPT MCP Server

7 tools. 5 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 11 Jun 2026

5 can modify or destroy data

2 read-only

7 tools total

Community server · catalogue entry verified 11/06/2026

How to control ChatGPT MCP Server ↓

TOOL MAP

What ChatGPT MCP Server exposes to your agents

Read (2) Write / Execute (4) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous ChatGPT MCP Server tools

Destructive · High container_remove Removing a container is a destructive action that cannot be undone without recreating the container from scratch. Execute · High container_exec This tool allows execution of arbitrary commands inside a Docker container. Execute · High container_start Starting a container executes arbitrary code or services defined within that container. Execute · High container_stop The tool executes a command that changes the operational state of a running container.

5 of ChatGPT MCP Server's 7 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control ChatGPT MCP Server

PolicyLayer is an MCP gateway — it sits between your AI agents and ChatGPT MCP Server, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "container_remove": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Cap read operations

{
  "container_logs": {
    "limits": [
      {
        "counter": "container_logs_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register ChatGPT MCP Server — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON CHATGPT →

Free to start. No card required.

FULL CATALOGUE

All 7 ChatGPT MCP Server tools

DESTRUCTIVE 1 tools

Destructive container_remove Remove a container

EXECUTE 4 tools

Execute container_exec Execute a command in a running container Execute container_start Start a stopped container Execute container_stop Stop a running container Execute container_create Create and start a new Docker container

READ 2 tools

Read container_logs Get container logs Read containers_list List all Docker containers

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about ChatGPT MCP Server

Can an AI agent delete data through the ChatGPT MCP Server MCP server? +

Yes. The ChatGPT MCP Server server exposes 1 destructive tools including container_remove. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How many tools does the ChatGPT MCP Server MCP server expose? +

7 tools across 4 categories: Destructive, Execute, Read, Write. 2 are read-only. 5 can modify, create, or delete data.

How do I enforce a policy on ChatGPT MCP Server? +

Register the ChatGPT MCP Server MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every ChatGPT MCP Server tool call.

Deterministic rules across all 7 ChatGPT MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON CHATGPT →

Free to start. No card required.

7 ChatGPT MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.