广告合作
MCP.so
登录

Flux Image Generator MCP Server

@frankdeno

代码仓库

基本信息

分类

开发工具

传输方式

stdio

作者

frankdeno

提交者

Frank Dierolf

关于 Flux Image Generator MCP Server

flux-image-generator-mcp

#flux-image-generator#image-generation#mcp-server

Flux Image Generator MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "flux-image-generator": {
      "command": "mcp-server-flux-image-generator",
      "env": {
        "BFL_API_KEY": "your_api_key_here"
      }
    }
  }
}

Flux Image Generator MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Flux Image Generator?

An MCP server that generates images using Black Forest Lab’s FLUX model. It integrates with MCP clients (e.g., Claude) and requires a Black Forest Lab API key. Aimed at developers and users who want to create AI-generated images with customizable settings.

How to use Flux Image Generator?

Install via npm (npm install -g @modelcontextprotocol/server-flux-image-generator) or from source. Configure your BFL_API_KEY in a .env file or client config. Start the server with npm start. Then invoke its tools (generateImage, quickImage, batchGenerateImages) from an MCP client.

Key features of Flux Image Generator

  • Generate images from text prompts with customizable dimensions.
  • Optional prompt upsampling for enhanced detail.
  • Safety tolerance setting for content moderation (1–5).
  • Batch generation of up to 10 images from multiple prompts.
  • Saves generated images locally and returns image URLs.

Use cases of Flux Image Generator

  • Generate concept art or illustrations for creative projects.
  • Quickly produce multiple image variants from a list of prompts.
  • Integrate AI image generation into chat or workflow tools via MCP.
  • Reproduce results using a fixed random seed.

常见问题

1

What API key is required?

A Black Forest Lab API key (obtained at https://api.bfl.ml) must be set as the `BFL_API_KEY` environment variable.

2

What are the supported image dimensions?

Width and height default to 1024 pixels and can be customized in `generateImage` and `batchGenerateImages`.

3

Can I batch generate images?

Yes, use the `batchGenerateImages` tool with up to 10 prompts. Each prompt can have different results.

4

How does content moderation work?

The `safetyTolerance` parameter (1–5, default 3) controls how strictly the model filters prohibited content. A violation returns an error.

5

Where are generated images saved?

Images are saved locally (paths shown in responses) and also returned via a temporary image URL from storage.example.com.

评论

开发工具 分类下的更多 MCP 服务器

Heard

Heard

Let your cloud agents talk to you. Grok Bot, Meta Muse, ChatGPT, Claude, Devin and others report progress to Heard, which reads it out loud on your Mac, and they pick up the replies you send back.

NextBlock CMS

NextBlock

Open-source Next.js + Supabase CMS with a per-site MCP server: scaffold a site, then create pages, posts, navigation, media and SEO from Claude, Cursor or any MCP client. Streamable HTTP with a bearer token you mint in y

Casefile

azimov777

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.

3

Nizh

Nizh

Compliance frameworks delivered to AI agents. Nizh gives your agent read access to your organization's compliance program — SOC 2, ISO 27001, CMMC 2.0, NIST, and more — as MCP tools, so it can check posture, read a contr

Foremerge

naw103

Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.

50
广告合作