Generate images with the catalogue's image model, returned inline; image price plus $0.01 a call.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Bearer followed by your TopxAI API key (create one at https://api.topxai.xyz/keys)
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Generate one or more images from a prompt with the TopxAI image model. Billed at the model's per-request price plus a $0.01 call fee. Returns the images inline and as temporary signed links valid for up to one hour; cache capacity may expire them earlier.
What to draw.
Number of images.
WIDTHxHEIGHT, for example 1024x1024, 1536x1024, 1024x1536 or 2048x2048.
Image model.
Optional rendering quality.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http images https://api.topxai.xyz/mcp/images \ --header 'Authorization: Bearer YOUR_TOKEN'
Headers
Authorization (required): Bearer followed by your TopxAI API key (create one at https://api.topxai.xyz/keys)Generate one or more images from a prompt with the TopxAI image model. Billed at the model's per-request price plus a $0.01 call fee. Returns the images inline and as temporary signed links valid for up to one hour; cache capacity may expire them earlier.
| Argument | Type | Description |
|---|
| n | integer | Number of images. |
| size | string | WIDTHxHEIGHT, for example 1024x1024, 1536x1024, 1024x1536 or 2048x2048. |
| model | string | Image model. |
| prompt* | string | What to draw. |
| quality | string | Optional rendering quality. |
{
"type": "object",
"required": [
"prompt"
],
"properties": {
"n": {
"type": "integer",
"default": 1,
"maximum": 4,
"minimum": 1,
"description": "Number of images."
},
"size": {
"type": "string",
"default": "1024x1024",
"description": "WIDTHxHEIGHT, for example 1024x1024, 1536x1024, 1024x1536 or 2048x2048."
},
"model": {
"type": "string",
"description": "Image model."
},
"prompt": {
"type": "string",
"description": "What to draw."
},
"quality": {
"enum": [
"low",
"medium",
"high"
],
"type": "string",
"description": "Optional rendering quality."
}
},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 13, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.