Skip to main content
Glama

Cloudflare Image MCP

Deploy to Cloudflare Workers

OpenAI-compatible image generation API + Streamable HTTP MCP server powered by Cloudflare Workers AI.

🌟 Features

  • OpenAI-Compatible API: /v1/images/generations + /v1/images/edits endpoints

  • MCP Protocol Support: HTTP transport with SSE (streamable)

  • 10 Image Generation Models: FLUX, SDXL, Stable Diffusion, and more

  • Multiple Tasks: Text-to-image, image-to-image (masked edits supported)

  • Web Frontend: Interactive UI for image generation

  • R2 Storage: Auto-expiring image storage with CDN

Related MCP server: openai-images-mcp

πŸ“¦ What's Included

cloudflare-image-mcp/
β”œβ”€β”€ workers/           # Cloudflare Worker (API + MCP + Frontend)
└── e2e/               # Playwright E2E tests

πŸš€ Quick Start

Prerequisites

  1. Deploy this MCP server to your Cloudflare account (takes 5 minutes): πŸ‘‰ Deployment Guide

  2. Note your worker URL after deployment:

    https://cloudflare-image-workers.<your-subdomain>.workers.dev
  3. If you set API_KEYS during deployment, you'll need the key for authentication.

MCP Client Configuration

Below are the configuration guides for different MCP clients. This server uses HTTP/SSE transport (not stdio) since it runs on Cloudflare Workers.

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "cloudflare-image": {
      "url": "https://your-worker.workers.dev/mcp"
    }
  }
}

If using API key authentication:

{
  "mcpServers": {
    "cloudflare-image": {
      "url": "https://your-worker.workers.dev/mcp?key=your-api-key"
    }
  }
}

Add the MCP server:

claude mcp add cloudflare-image https://your-worker.workers.dev/mcp

With API key:

claude mcp add cloudflare-image https://your-worker.workers.dev/mcp?key=your-api-key

Go to: Settings β†’ Cursor Settings β†’ MCP β†’ Add new global MCP server

{
  "mcpServers": {
    "cloudflare-image": {
      "url": "https://your-worker.workers.dev/mcp"
    }
  }
}

Open Cline β†’ Click MCP Servers icon β†’ Installed tab β†’ Advanced MCP Settings

Add to cline_mcp_settings.json:

{
  "mcpServers": {
    "cloudflare-image": {
      "url": "https://your-worker.workers.dev/mcp"
    }
  }
}

This server implements the MCP HTTP/SSE transport. Configure your client with:

  • Transport: HTTP/SSE (streamable)

  • URL: https://your-worker.workers.dev/mcp

  • Auth (if API_KEYS set): Add ?key=your-api-key to the URL


πŸ“– Usage

OpenAI-Compatible API

curl -X POST "https://your-worker.workers.dev/v1/images/generations" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key" \
  -d '{
    "model": "@cf/black-forest-labs/flux-1-schnell",
    "prompt": "A beautiful sunset over mountains",
    "n": 1,
    "size": "1024x1024"
  }'

And it can be used for OpenWebUI's image generation feature and image edits feature:

OpenWebUI image generation

OpenWebUI image_edits

MCP Tools

Available Tools:

  • list_models - List all available models

  • describe_model - Get model parameters and limits

  • run_model - Generate images

Connect via MCP:

{
  "mcpServers": {
    "image-gen": {
      "url": "https://your-worker.workers.dev/mcp"
    }
  }
}

Web Frontend

Open your worker URL in a browser for an interactive UI.

Frontend


🎨 Supported Models

πŸ“‹ Detailed Model Specifications β†’ β€” Full parameter reference, feature comparison, and capability matrix.

Model

Tasks

Provider

FLUX.1 [schnell]

text-to-image

Black Forest Labs

FLUX.2 [klein]

text-to-image, image-to-image

Black Forest Labs

FLUX.2 [dev]

text-to-image, image-to-image

Black Forest Labs

SDXL Base 1.0

text-to-image, image-to-image (img2img + masked edits)

Stability AI

SDXL Lightning

text-to-image

ByteDance

Dreamshaper 8 LCM

text-to-image, image-to-image (img2img)

Lykon

Lucid Origin

text-to-image

Leonardo

Phoenix 1.0

text-to-image

Leonardo

SD 1.5 Img2Img

image-to-image (img2img)

Runway ML

SD 1.5 Inpainting

image-to-image (requires mask)

Runway ML


πŸ“š Documentation

Document

Description

Deployment Guide

Step-by-step deployment instructions

Credentials Setup

Environment variables and API tokens

Usage Guide

Detailed API usage examples

MCP Guide

MCP protocol and tools reference

API Reference

REST endpoints documentation


πŸ§ͺ Testing

# Run E2E tests against staging/production
npm run test:e2e:staging
npm run test:e2e:production

πŸ”§ Development

# Type check
npm run build

# Run E2E tests
npm run test:e2e:staging

πŸ“ License

MIT


Built with:

Related MCP Connectors

Related MCP Servers