Pixola / Docs / MCP Server

MCP Server

Use Pixola directly from ChatGPT, Claude, Cursor, or any MCP-compatible AI tool — generate images, browse models, and check credits without leaving your conversation.

What is MCP?

The Model Context Protocol (MCP) lets AI assistants call external tools. Once configured, you can prompt your AI to generate images, check your credits, or browse your image history — and it will call Pixola automatically. No copy-pasting API keys or writing code.

How it works

Pixola can be used in two ways:

Remote MCP (hosted): Your app talks over the internet to https://www.pixola.ai/mcp. You add the URL and API key in the app's config. No local install. Used by ChatGPT, Cursor, Windsurf, VS Code, Claude Code, and Claude Desktop.
Local MCP (Claude Desktop only): The .mcpb extension installs a small server that runs on your computer; that server calls Pixola's API. Used only when you install the one-click extension in Claude Desktop.

https://www.pixola.ai/mcp

Remote MCP endpoint. Uses Streamable HTTP and Bearer token auth.

Setup guides

Step-by-step instructions for each platform:

ChatGPT →Pro / Team / Enterprise Claude Desktop →One-click or manual Claude Code →Terminal agent Cursor →AI code editor Windsurf →AI code editor VS Code / Copilot →GitHub Copilot

Interactive apps

On hosts that support MCP Apps, some tools render an interactive UI right in your conversation — a form, gallery, or dashboard — instead of just text. The same tools work everywhere; supported hosts just show a richer experience. Nothing extra to configure.

generate_imageGenerate one or more AI images from a text prompt. Polls automatically and returns image URLs when ready. Supports all 40+ models, style presets, aspect ratios, and quality tiers.

list_modelsList all available AI image generation models with their slugs, descriptions, and credit pricing.

check_creditsCheck your current credit balance and subscription plan.

list_imagesList your recently generated images with titles, models used, and URLs.

get_imageGet full details and download URL for a specific image.

Supported hosts: Claude (web + Desktop), VS Code Copilot, Goose, Postman, MCPJam. Other hosts receive the standard text response — no change to behavior.

Available tools

The MCP server exposes 8 tools your AI assistant can call.

generate_image(prompt, model?, style?, shape?, quality?)Interactive UI

Generate one or more AI images from a text prompt. Polls automatically and returns image URLs when ready. Supports all 40+ models, style presets, aspect ratios, and quality tiers.

list_models()Interactive UI

List all available AI image generation models with their slugs, descriptions, and credit pricing.

list_styles()

List all style presets organized by category (e.g. watercolor, anime, art-deco, oil-painting).

list_shapes()

List all aspect ratio options with their slugs and dimensions (e.g. square, landscape-wide, portrait-tall).

check_credits()Interactive UI

Check your current credit balance and subscription plan.

get_batch(batchId)

Check the status of an image generation batch and retrieve image URLs when complete.

list_images(limit?)Interactive UI

List your recently generated images with titles, models used, and URLs.

get_image(imageId)Interactive UI

Get full details and download URL for a specific image.

Example prompts

Once configured, try asking your AI assistant things like:

“Generate a widescreen landscape image using FLUX 2 in watercolor style”

“What models are available and how many credits do they cost?”

“Show me my last 10 generated images”

“How many credits do I have left?”

“Generate 3 versions of a neon city at night — try different styles”

Any MCP client

For any client that supports remote MCP servers with Streamable HTTP transport:

URL	https://www.pixola.ai/mcp
Transport	Streamable HTTP (POST)
Auth header	Authorization: Bearer pxk_YOUR_API_KEY
Content type	application/json

Test with curl:

curl -X POST https://www.pixola.ai/mcp \
  -H "Authorization: Bearer pxk_YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -d '{"jsonrpc":"2.0","method":"tools/list","id":1}'

Authentication

The server requires a Pixola API key passed as a Bearer token in the Authorization header. Most MCP clients handle this automatically when you configure the server.

Authorization: Bearer pxk_...

Create your key at Settings → API Keys. Keys start with pxk_ and are shown only once at creation time.

Rate limits

30 requests per minute per API key

1,000 requests per day per API key

These are the same limits as the REST API.

Get started

Create a free API key and connect Pixola to your AI assistant in under a minute.