mcpField
C
CF-MCP-Server

CF-MCP-Server

Local
github.com/turinhubMedia & Design0Updated 73w ago
Repository

About CF-MCP-Server

CF-MCP-Server is an image-generation MCP service built with Cloudflare Workers for applications that need image generation through MCP. It uses Flux-1-Schnell and returns images as Base64-encoded PNGs.

Key features

  1. 01MCP image-generation interface
  2. 02Uses the Flux-1-Schnell model
  3. 03Configurable 4–8 generation steps
  4. 04Returns Base64-encoded PNGs
  5. 05Extensible custom tools and resources

Use cases

  1. 01Generate images for MCP clients
  2. 02Adjust generation steps for image processing
  3. 03Deploy an image service on Cloudflare Workers

MCP support

The service exposes image generation to MCP clients and supports extending the server with custom tools and resources.

Configuration

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

mcp.json · Universal config
{
  "mcpServers": {
    "cf-mcp-server-turinhub": {
      "command": "npx",
      "args": [
        "-y",
        "create-cloudflare"
      ]
    }
  }
}
Run commandnpx -y create-cloudflare

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmcreate-cloudflare

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

CF-MCP-Server

License: MIT Cloudflare Workers

基于 Model Context Protocol (MCP) 的图像生成服务实现，采用 Cloudflare Workers 构建。

核心功能

  • 🖼️ 基于 MCP 协议的标准化服务接口
  • 🚀 开箱即用的图像生成 Worker 模块
  • 🔧 支持快速扩展自定义工具和资源
  • ⚡ 边缘计算优化部署

模块构成

mcp-image-generation
graph LR
    subgraph mcp-image-generation
    A[Cloudflare Worker] --> B[Flux-1-Schnell 模型]
    A --> C[图像生成API]
    C --> D((4-8 steps))
    end
  • 支持步骤数范围：4-8 steps
  • 响应格式：Base64 编码的 PNG 图像
  • 部署方式：Cloudflare Workers

快速开始

环境要求
  • Node.js 18+
  • Wrangler CLI
  • NPM
安装部署
# 安装依赖
pnpm install

# 配置环境变量
cp .env.example .env

# 部署Worker
pnpm deploy

API 文档

图像生成接口

配置示例:

{
  "mcpServers": {
    "generateImage": {
      "command": "/Users/zhangxudong/Gits/turinhub/cf-mcp-server/mcp-image-generation/node_modules/.bin/workers-mcp",
      "args": [
        "run",
        "generateImage",
        "https://mcp-image-generation.turinhub.com",
        "/Users/zhangxudong/Gits/turinhub/cf-mcp-server/mcp-image-generation"
      ],
      "env": {}
    }
  }
}

参数说明:

参数类型约束说明
promptstring1-500字符英文描述提示词
stepsnumber4 ≤ steps ≤ 8生成迭代步数

开发指南

添加新工具

参考在线文档 官方案例代码库

  1. 使用 MCP SDK 创建新 Worker：
npx create-cloudflare@latest my-new-worker
cd my-new-worker # I always forget this bit
npm install workers-mcp
npx workers-mcp setup

注意：不要在项目本地 package.json 安装 wrangler，直接使用全局管理。

  1. 实现工具逻辑后更新主服务配置
  2. 使用 @modelcontextprotocol/inspector 测试 MCP
npx @modelcontextprotocol/inspector

贡献说明

欢迎通过 Issue 和 PR 参与贡献，请遵循现有代码风格。

许可证

MIT License © 2025 Turinhub

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.