Cloudflare Image MCP
An MCP server that allows AI models to generate images from text prompts and describe images using Cloudflare Workers AI models.
README
opencode-cloudflare-image-mcp
An MCP (Model Context Protocol) server that gives any MCP-capable AI model (Claude Desktop, opencode, etc.) the ability to generate images from text prompts and describe images in text, using Cloudflare Workers AI models.
Features
- generate_image — Generate images from text prompts using Cloudflare text-to-image models (FLUX.1 Schnell, SDXL, DreamShaper, and more).
- describe_image — Generate text descriptions of images using Cloudflare image-to-text models (LLaVA, Moondream, uForm).
- list_models — Discover all supported models with aliases and defaults.
- Generated images are saved to disk; the file path is returned to the model.
- Image-to-text supports both local file paths and HTTP(S) URLs as input.
Install via OpenCode Agent
Paste this to your opencode agent to install and configure:
Install the opencode-cloudflare-image-mcp MCP server globally, then add it to my opencode.json config at ~/.config/opencode/opencode.json as a local MCP server with:
- type: local
- command: ["node", "E:/Image-MCP/dist/index.js"] (or your install path)
- environment with CLOUDFLARE_ACCOUNT_ID and CLOUDFLARE_API_TOKEN
Or manually:
npm install -g opencode-cloudflare-image-mcp
Then add to ~/.config/opencode/opencode.json:
{
"mcp": {
"cloudflare-image": {
"type": "local",
"command": ["node", "E:/Image-MCP/dist/index.js"],
"environment": {
"CLOUDFLARE_ACCOUNT_ID": "your-account-id",
"CLOUDFLARE_API_TOKEN": "your-api-token"
},
"enabled": true
}
}
}
Note: Use
"environment"not"env"for the env vars in opencode config.
Install (Manual)
npm install -g opencode-cloudflare-image-mcp
Or use directly with npx:
npx opencode-cloudflare-image-mcp
Configuration
Environment Variables
| Variable | Required | Default | Purpose |
|---|---|---|---|
CLOUDFLARE_ACCOUNT_ID |
yes | — | Cloudflare account ID |
CLOUDFLARE_API_TOKEN |
yes | — | Bearer token for API auth |
IMAGE_MCP_OUTPUT_DIR |
no | ./generated-images |
Where generated PNG files are saved |
IMAGE_MCP_DEFAULT_T2I_MODEL |
no | @cf/black-forest-labs/flux-1-schnell |
Default text-to-image model |
IMAGE_MCP_DEFAULT_I2T_MODEL |
no | @cf/llava-hf/llava-1.5-7b-hf |
Default image-to-text model |
Getting a Cloudflare API Token
- Go to the Cloudflare dashboard.
- Navigate to My Profile → API Tokens.
- Click Create Token.
- Use the Workers AI template, or create a custom token with
Workers AI:Readpermission. - Copy the token and set it as
CLOUDFLARE_API_TOKEN.
Your Cloudflare Account ID is visible on the dashboard overview page or any domain's overview page.
Client Configuration
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"cloudflare-image": {
"command": "npx",
"args": ["-y", "opencode-cloudflare-image-mcp"],
"env": {
"CLOUDFLARE_ACCOUNT_ID": "your-account-id",
"CLOUDFLARE_API_TOKEN": "your-api-token"
}
}
}
}
opencode / Generic stdio
{
"mcp": {
"cloudflare-image": {
"type": "local",
"command": ["npx", "-y", "opencode-cloudflare-image-mcp"],
"env": {
"CLOUDFLARE_ACCOUNT_ID": "your-account-id",
"CLOUDFLARE_API_TOKEN": "your-api-token"
}
}
}
}
Usage
Once connected, the AI model can call these tools:
generate_image
Generate an image of a cyberpunk lizard in a neon-lit city
The model will call generate_image with the prompt. The image is saved to disk and the file path is returned.
describe_image
Describe the image at /path/to/image.png
Or with a URL:
What's in this image? https://example.com/photo.jpg
list_models
What image models are available?
Supported Models
Text-to-Image
| Alias | Model ID | Default |
|---|---|---|
flux-schnell |
@cf/black-forest-labs/flux-1-schnell |
yes |
flux-2-klein-4b |
@cf/black-forest-labs/flux-2-klein-4b |
|
sdxl-lightning |
@cf/bytedance/stable-diffusion-xl-lightning |
|
dreamshaper |
@cf/lykon/dreamshaper-8-lcm |
|
sdxl-base |
@cf/stabilityai/stable-diffusion-xl-base-1.0 |
Image-to-Text
| Alias | Model ID | Default |
|---|---|---|
llava |
@cf/llava-hf/llava-1.5-7b-hf |
yes |
uform |
@cf/unum/uform-gen2-qwen-500m |
|
moondream |
@cf/moondream/moondream3.1-9B-A2B |
Development
pnpm install
pnpm test
pnpm build
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。