The same eleven tools, from the OpenAI side of the fence.
The server is a standard remote MCP endpoint. That makes it reachable from ChatGPT’s custom connectors where your account has them, from the OpenAI Agents SDK, from the Responses API, and — if you would rather skip MCP entirely — from plain REST calls in any language.
Endpoint
https://mcp.imagemcpserver.com/mcpStreamable HTTP. No SDK required.
Auth header
x-api-key: sk-img-gen-…Authorization: Bearer also accepted.
URL-only clients
?apikey=sk-img-gen-…For clients that cannot send headers.
A straight answer about the ChatGPT app
Custom MCP connectors in the ChatGPT app are gated by plan and by developer-mode settings, and OpenAI has moved that surface more than once. Rather than print a click path that may be stale by the time you read it, this page gives you the two things that do not change — the endpoint and the auth — plus a route through the API that works today regardless of what the app offers your account.
Three ways in
ChatGPT custom connector
Where your account offers custom connectors, add a new one, give it the endpoint above, and supply the API key as a header. The image tools then appear in the conversation the same way any other connector’s do. If you do not see the option, that is a plan or settings question for OpenAI, not a limitation of the server.
Server URL
https://mcp.imagemcpserver.com/mcpHeader
x-api-key: sk-img-gen-…OpenAI Agents SDK / Responses API
Both accept a hosted MCP server as a tool source. You register the endpoint once and the model can call any of the eleven tools during a run — which is the route to take when you are building a product rather than chatting.
tools: [
{
type: "mcp",
server_label: "imagemcp",
server_url: "https://mcp.imagemcpserver.com/mcp",
headers: {
"x-api-key": process.env.IMAGEMCP_API_KEY
}
}
]Skip MCP — call the REST API
Every tool is also a plain HTTP endpoint. If you are writing the orchestration yourself, there is no reason to add a protocol layer between your code and a POST request.
await fetch(
"https://api.imagemcpserver.com/playground/generate",
{
method: "POST",
headers: {
Authorization: `Bearer ${key}`,
"Content-Type": "application/json",
},
body: JSON.stringify({ prompt, aspectRatio: "16:9" }),
}
);What you get that a built-in image feature does not give you
A ledger
Every call recorded with its tool, model and exact credit cost. Not an estimate — the number you were charged.
Eight operations
Generation is one of them. Cutting out, upscaling, vectorising and compressing are the ones that turn an image into an asset.
Model choice
Route to a fast model for drafts and a premium one for finals, or bring your own OpenRouter key and pay the provider directly.
Portability
The same key and the same tools work from Claude, Cursor, VS Code, a cron job and your production backend.
ChatGPT & OpenAI questions
Can ChatGPT use any MCP server?
ChatGPT supports custom MCP connectors, but availability and the exact setup path depend on your plan and on whether developer mode is enabled for your account. The endpoint and the auth header below are what you need wherever the option is available to you; the UI around it is OpenAI’s and it moves.
What is the endpoint and how do I authenticate?
The server speaks streamable HTTP MCP at https://mcp.imagemcpserver.com/mcp. Authenticate with your API key as an x-api-key header, an Authorization: Bearer header, or an ?apikey= query parameter when a client only supports URLs.
What if my ChatGPT plan has no connector option?
Use the API instead of the app. The OpenAI Agents SDK and the Responses API both accept a remote MCP server, so the same eleven tools are available to anything you build — and the REST endpoints work from any language with no MCP layer at all.
Is this different from ChatGPT’s own image generation?
Yes, in what surrounds it. This gives you a credit ledger you can read, a request log per call, a choice of underlying models including your own OpenRouter account, and eight distinct operations — background removal, upscaling, vector output, compression — rather than generation alone.
Does it work with other MCP-capable assistants?
Any client that speaks the Model Context Protocol can connect. The remote endpoint is standard streamable HTTP, and there is a stdio process for clients that prefer to spawn one locally.