返回 MCP 目录
public公开dns本地运行

MCP视觉生成器

这是一款基于 FAL AI 技术的服务器,具备徽标生成功能,同时配备图像生成、背景移除以及自动缩放等工具。

article

README

MCP Tool Server for Logo Generation

This server provides logo generation capabilities using FAL AI, with tools for image generation, background removal, and automatic scaling.

Demo

MCP Tool Server Demo

Installation

  1. Install uv (Universal Virtualenv):
curl -LsSf https://astral.sh/uv/install.sh | sh
  1. Create and activate a virtual environment:
uv venv
source .venv/bin/activate  # On Unix/macOS
# or
.venv\Scripts\activate     # On Windows
  1. Install dependencies:
uv pip install -r requirements.txt
  1. Set up your environment variables:
    • Create a .env file in the root directory
    • Add your FAL AI API key:
FAL_KEY=your_fal_ai_key_here

Running the Server

Start the server with:

python run_server.py

The server will be available at http://127.0.0.1:7777

Troubleshooting

If you encounter a FileNotFoundError on Windows when running the server, make sure you're running the command from the root directory of the project. If the issue persists, try updating to the latest version of the repository which includes fixes for Windows compatibility.

For Windows users specifically:

  1. Make sure you've activated your virtual environment with .venv\Scripts\activate
  2. Run the server from the root directory of the project with python run_server.py
  3. If you see any path-related errors, please report them in the issues section of the repository

Cursor IDE Configuration

  1. Open Cursor Settings
  2. Navigate to the MCP section
  3. Add the following configuration:
    • URL: http://127.0.0.1:7777/sse
    • Connection Type: SSE
    • Enable the connection

Notes

  • Always reference @logo-creation.mdc in your Cursor Composer for consistent results
  • Steps are defined in @logo-creation.mdc but tools can be used independently
  • All generated logos will be saved in the downloads directory
  • Each logo is automatically generated in three sizes:
    • Original size
    • 32x32 pixels
    • 128x128 pixels
  • All logos maintain transparency in their final PNG format
  • Prompts created by agent are informed by examples and prompt structure seen in server.py. You can customize the prompt structure by editing the server.py file.
  • You can use the generate_image tool to generate any image you want, not just logos

Requirements

  • Python 3.8+
  • FAL AI API key (required for image generation)
  • Active internet connection

References


If you find this tool helpful, you can buy me a coffee ☕️ to support development!

help

运行方式说明

cloud

托管运行

托管运行通常表示这个 MCP Server 由服务方环境承载,用户一般按页面提供的连接方式或授权流程接入,不需要在本地长期启动一个 MCP 进程

  1. 打开服务方连接页
  2. 完成授权或复制端点
  3. 在 MCP 客户端中连接
terminal

本地运行 / 其它方式

本地运行通常需要用户在自己的电脑或服务器上安装依赖,把 server_config 复制到 MCP 客户端,并按 env_schema 补齐环境变量、密钥或其它配置

  1. 复制 server_config
  2. 安装所需依赖
  3. 补齐环境变量后重启客户端