mcpField
F
Flux Schnell MCP Server

Flux Schnell MCP Server

Local
github.com/ckzMedia & Design2Updated 85w ago

About Flux Schnell MCP Server

Flux Schnell MCP Server lets MCP-compatible clients generate images with the Flux Schnell model through the Replicate API. It accepts a text prompt and returns the API response, including the image URL and metadata.

Key features

  1. 01Generate images with Flux Schnell
  2. 02Accept custom text prompts
  3. 03Call the Replicate API
  4. 04Return image URLs and metadata
  5. 05Handle errors and responses

Use cases

  1. 01Generating images from text descriptions
  2. 02Creating images in a compatible MCP environment

MCP support

Exposes a `generate_image` tool to MCP clients. The tool accepts a required `prompt` and returns the Replicate API response.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Flux Schnell MCP Server

一个基于MCP(Model Context Protocol)的服务器,用于通过Replicate API调用Flux Schnell模型生成图片。

功能特点

  • 提供generate_image工具用于生成图片
  • 支持自定义文本提示词
  • 自动处理与Replicate API的通信
  • 完整的错误处理和响应

前置要求

  1. Node.js (v14或更高版本)
  2. Replicate API Token
  3. MCP兼容的环境(如Claude Desktop)

获取Replicate API Token

  1. 访问 Replicate官网 并注册账号
  2. 登录后访问 API Tokens页面
  3. 点击"Create API token"创建新的token
  4. 复制生成的token(格式如:r8_xxxxxx)

安装

  1. 克隆项目并安装依赖:
git clone [repository-url]
cd flux-schnell-mcp
npm install
  1. 构建服务器:
npm run build

配置

Claude Desktop配置
  1. 打开配置文件:

    • MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
    • Windows: %APPDATA%/Claude/claude_desktop_config.json
  2. 添加服务器配置:

{
  "mcpServers": {
    "flux-schnell": {
      "command": "node",
      "args": ["/path/to/flux-schnell-mcp/build/index.js"],
      "env": {
        "REPLICATE_API_TOKEN": "your-replicate-api-token"
      },
      "disabled": false,
      "alwaysAllow": []
    }
  }
}
VSCode Roo配置
  1. 打开配置文件:

    • Linux: ~/.vscode-remote/data/User/globalStorage/rooveterinaryinc.roo-cline/settings/cline_mcp_settings.json
    • MacOS: ~/Library/Application Support/Code/User/globalStorage/rooveterinaryinc.roo-cline/settings/cline_mcp_settings.json
    • Windows: %APPDATA%/Code/User/globalStorage/rooveterinaryinc.roo-cline/settings/cline_mcp_settings.json
  2. 添加与上述相同的服务器配置。

使用方法

服务器提供了一个名为generate_image的工具,可以通过MCP调用:

<use_mcp_tool>
<server_name>flux-schnell</server_name>
<tool_name>generate_image</tool_name>
<arguments>
{
  "prompt": "a beautiful sunset over the ocean, digital art style"
}
</arguments>
</use_mcp_tool>
参数说明
  • prompt: 用于生成图片的文本描述(必填)
    • 建议使用详细的描述来获得更好的生成结果
    • 可以包含风格、场景、细节等信息
响应格式

服务器将返回Replicate API的完整响应,包含生成的图片URL和其他元数据。

调试

由于MCP服务器通过stdio通信,调试可能比较困难。推荐使用MCP Inspector:

npm run inspector

Inspector将提供一个URL,可以在浏览器中访问调试工具。

注意事项

  1. 请妥善保管您的Replicate API Token,不要将其分享给他人
  2. 确保在配置文件中使用正确的文件路径
  3. 生成图片可能需要一些时间,请耐心等待响应
  4. 如遇到错误,请检查API Token是否正确,以及网络连接是否正常

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.