mcp_generate_images
by: chenyeju295
可用于cursor 集成 mcp server
📌Overview
Purpose: The AI image generation service leverages Together AI technology to facilitate seamless image creation, specifically designed for integration with Cursor MCP services.
Overview: This framework offers a robust solution for generating high-quality images with features that support custom configurations such as image size and storage paths. It is well-suited for projects needing automated and error-tolerant image generation capabilities.
Key Features:
-
High-Quality Image Generation: Ensures the creation of visually appealing images suitable for various applications.
-
Automatic Retry and Error Handling: Enhances reliability by automatically retrying failed requests and providing detailed error messages, significantly improving the user experience.
-
Batch Image Generation Support: Allows for the simultaneous creation of multiple images, optimizing workflow efficiency.
-
Path and Permission Verification: Validates paths and permissions to ensure successful image saving operations.
-
Asynchronous Processing Support: Facilitates non-blocking operations that can improve performance in handling multiple requests simultaneously.
AI 图像生成服务
基于 Together AI 的图像生成服务,专门设计用于与 Cursor MCP 服务集成。支持自定义图片大小、保存路径等功能。
功能特点
- 支持高质量图像生成
- 自动重试和错误处理
- 支持批量生成多张图片
- 完整的路径和权限验证
- 详细的错误提示
- 异步处理支持
环境准备
1. Python 环境
- Python 3.10+ (推荐使用 pyenv 管理 Python 版本)
# 安装 pyenv
brew install pyenv
# 安装 Python
pyenv install 3.13.2
pyenv global 3.13.2
- Nodejs 环境(下载地址:Node.js)
2. uv 包管理工具
安装 uv 包管理器:
# 安装 uv
brew install uv
# 或者使用 pip 安装
pip install uv
3. Together AI API 密钥
- 访问 Together AI API Keys
- 注册/登录账号
- 创建新的 API 密钥并保存
4. Cursor
下载并安装 Cursor IDE并确保配置了 Python 环境。
安装配置
- 克隆项目:
git clone https://github.com/chenyeju295/mcp_generate_images.git
- 安装依赖:
cd mcp_generate_images
python3 -m pip install fastmcp requests
如果出现证书问题,可以使用:
python3 -m pip install fastmcp requests --trusted-host pypi.org --trusted-host files.pythonhosted.org --upgrade --force-reinstall --no-cache-dir
- 配置 API 密钥:
在 mcp_server.py
中修改 TOGETHER_API_KEY
:
TOGETHER_API_KEY = "your_api_key_here" # 替换为你的 Together AI API 密钥
- 配置服务:
在 mcp_server.py
中可以修改以下配置:
CONFIG = {
"api": {
"url": "https://api.together.xyz/v1/images/generations",
"model": "black-forest-labs/FLUX.1-schnell-Free",
"timeout": 30,
"max_retries": 3,
"retry_delay": 5
},
"image": {
"max_width": 1024,
"max_height": 1024,
"default_width": 1024,
"default_height": 1024,
"default_steps": 2,
"max_batch_size": 4
},
"output": {
"base_folder": "你的默认保存路径",
"allowed_extensions": [".png", ".jpg", ".jpeg"],
"default_extension": ".png"
}
}
运行服务
- 开发模式运行(带调试界面):
uv run --with fastmcp fastmcp dev /Users/username/Documents/mcp_generate_images/mcp_server.py
- 生产模式运行:
uv run --with fastmcp fastmcp run /Users/username/Documents/mcp_generate_images/mcp_server.py
- 如果端口被占用,可以指定其他端口:
PORT=5174 uv run --with fastmcp fastmcp dev /Users/username/Documents/mcp_generate_images/mcp_server.py
使用说明
在 Cursor IDE 中使用
- 确保服务正在运行。
- 在 Cursor 中引入 MCP:
uv run --with fastmcp fastmcp run /Users/username/Documents/mcp_generate_images/mcp_server.py
- 在 Cursor 中使用: 直接输入相关的提示。
错误排查
如果遇到问题,请检查:
- 服务是否正常运行
- 保存路径是否正确(必须是绝对路径)
- 目录权限是否正确
- 网络连接是否正常
- API 密钥是否有效
- Python 环境是否正确配置
- uv 是否正确安装
- 依赖包是否完整安装