Flux cf
@Hzzy2O
Flux cf について
概要はまだありません
基本情報
設定
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"Flux cf": {
"command": "npx",
"args": [
"-y",
"@smithery/cli@latest",
"run",
"@Hzzy2O/flux-cloudfare-mcp",
"--config",
"\"{\\\"fluxApiToken\\\":\\\"AIzaSyCb_wdwMQa_u3KHkd1ywHptTh_Rf07-bJU\\\",\\\"fluxApiUrl\\\":\\\"https://flux-api.capiiii664.workers.dev\\\"}\""
]
}
}
}ツール
ツールは検出されませんでした
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
概要
What is Flux cf?
Flux cf is an MCP server that enables AI assistants to generate images using Black Forest Labs' Flux model via a Cloudflare Worker API. It is intended for developers integrating image generation into MCP-compatible clients like Cursor, Claude Desktop, Cline, or Zed.
How to use Flux cf?
Install and run directly with npx, setting the FLUX_API_TOKEN and FLUX_API_URL environment variables. Alternatively, clone the repository, install dependencies, and build from source. Configure the server in your MCP client (e.g., Cursor or Claude Desktop) using the command env FLUX_API_TOKEN=YOUR_TOKEN FLUX_API_URL=YOUR_API_URL npx -y flux-cloudflare-mcp.
Key features of Flux cf
- High-quality image generation via the Flux model
- Seamless integration with MCP-compatible AI assistants
- Customizable parameters: aspect ratio, inference steps
- Local processing through a Cloudflare Worker endpoint
- Chat completions available using the same API
Use cases of Flux cf
- Generate images directly from within an AI assistant like Claude
- Customize image output with prompts, steps, and aspect ratios
- Deploy a light‑weight image generation API on Cloudflare Workers
FAQ from Flux cf
What does Flux cf need to run?
It requires a deployed Flux API endpoint (from snakeying/flux-api-worker or aigem/cf-flux-remix) and the corresponding FLUX_API_TOKEN and FLUX_API_URL environment variables.
How do I deploy the required Flux API?
You can deploy using snakeying/flux-api-worker (a simple Cloudflare Worker) or aigem/cf-flux-remix (a feature‑rich implementation with a web UI). Follow the instructions in each repository.
What parameters can I pass to generate_image?
The tool accepts a required prompt, an optional num_inference_steps (1‑4, default 4), and an optional aspect_ratio (e.g., "16:9", default "1:1").
Does the model have any safety filters?
Yes, the Flux model includes a built‑in safety filter that may block certain prompts.
What transports or authentication does the server use?
The server uses environment‑variable‑based authentication (FLUX_API_TOKEN) and connects to the Flux API over standard HTTPS. It is MCP‑compatible via the Model Context Protocol SDK.
「その他」の他のコンテンツ
Inbox Zero AI
elie222The world's best AI personal assistant for email. Open source app to help you reach inbox zero fast.
Blender
ahujasidOpen-source MCP to use Blender with any LLM
Maestro
mobile-dev-incPainless E2E Automation for Mobile and Web
Awesome Mlops
visengerA curated list of references for MLOps
Codelf
unbugA search tool helps dev to solve the naming things problem.
コメント