3D Cartoon Generator & File System MCP Server
Enables high-quality 3D-style cartoon image generation using Google Gemini AI alongside secure file system operations like reading, writing, and managing directories. It provides a dual-purpose toolkit for creative asset generation and local file management via the Model Context Protocol.
README
MCP Combined Server: 3D Cartoon Generator & File System Tools
A professional-grade server that provides two major capabilities:
- High-quality 3D-style cartoon image generation using Google's Gemini AI
- Secure file system operations for reading, writing, and managing files

🌟 Features
Image Generation
- 3D Cartoon Generation: Creates high-quality 3D-style cartoon images
- Child-Friendly Design: Focuses on colorful, playful, and engaging visuals
- Instant Preview: Automatically opens generated images in your default browser
- Local Storage: Saves images and previews in an organized output directory
File System Operations
- Secure File Access: Path validation and security checks
- Read/Write Files: Read and write text file contents
- Directory Operations: List, create, and navigate directories
- File Search: Find files matching patterns
System Features
- Professional Configuration: Robust error handling and controlled logging
- Cross-Platform Support: Intelligent file path handling for Windows, macOS, and Linux
- Smart OS Detection: Automatically finds the best save location for each operating system
- Security Controls: Restricted directory access through configuration
🛠️ Technical Stack
- Core Framework: Model Context Protocol (MCP) SDK
- AI Integration: Google Generative AI (Gemini)
- Runtime: Node.js v14+
- Language: TypeScript
- Package Manager: npm
📋 Prerequisites
- Node.js (v14 or higher)
- Google Gemini API key
- TypeScript
⚙️ Installation
- Clone the repository:
git clone https://github.com/falahgs/mcp-3d-style-cartoon-gen-server.git
cd mcp-3d-style-cartoon-gen-server
- Install dependencies:
npm install
- Configure environment:
Create a
.envfile in the root directory:
GEMINI_API_KEY=your_api_key_here
ALLOWED_DIRECTORIES=/path/to/allowed/dir1,/path/to/allowed/dir2
- Build the project:
npm run build
🔧 Configuring Claude Desktop with MCP Server
To integrate this combined server with Claude Desktop:
-
Locate the Configuration File:
- Windows:
%APPDATA%\Claude\claude_desktop_config.json - macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
- Windows:
-
Add the following configuration:
{
"mcpServers": {
"mcp-3d-cartoon-generator": {
"command": "node",
"args": [
"path/to/your/build/index.js"
],
"env": {
"GEMINI_API_KEY": "your_gemini_api_key_here",
"IS_REMOTE": "true",
"SAVE_TO_DESKTOP": "true",
"DETECT_OS_PATHS": "true",
"ALLOWED_DIRECTORIES": "C:\\Users\\YourUsername\\Desktop,C:\\Users\\YourUsername\\Documents",
"DEBUG": "false"
}
}
}
}
Windows PowerShell Helper Script
For Windows users, you can use the included fix_claude_config.ps1 script to automatically configure Claude Desktop:
- Edit the script to update the path to your server build and your Gemini API key
- Run the script in PowerShell:
powershell -ExecutionPolicy Bypass -File .\fix_claude_config.ps1
This will create or update the configuration file with proper encoding and settings.
🚀 Available Tools
1. Image Generation Tool
{
"name": "generate_3d_cartoon",
"description": "Generates a 3D style cartoon image for kids based on the given prompt",
"inputSchema": {
"type": "object",
"properties": {
"prompt": {
"type": "string",
"description": "The prompt describing the 3D cartoon image to generate"
},
"fileName": {
"type": "string",
"description": "The name of the output file (without extension)"
}
},
"required": ["prompt", "fileName"]
}
}
2. File System Tools
Read File
{
"name": "read_file",
"description": "Read the contents of a file",
"inputSchema": {
"type": "object",
"properties": {
"path": {
"type": "string",
"description": "Path to the file to read"
}
},
"required": ["path"]
}
}
Write File
{
"name": "write_file",
"description": "Write content to a file",
"inputSchema": {
"type": "object",
"properties": {
"path": {
"type": "string",
"description": "Path to the file to write"
},
"content": {
"type": "string",
"description": "Content to write to the file"
}
},
"required": ["path", "content"]
}
}
List Directory
{
"name": "list_directory",
"description": "List the contents of a directory",
"inputSchema": {
"type": "object",
"properties": {
"path": {
"type": "string",
"description": "Path to the directory to list"
}
},
"required": ["path"]
}
}
Create Directory
{
"name": "create_directory",
"description": "Create a new directory",
"inputSchema": {
"type": "object",
"properties": {
"path": {
"type": "string",
"description": "Path to the directory to create"
}
},
"required": ["path"]
}
}
Search Files
{
"name": "search_files",
"description": "Search for files matching a pattern",
"inputSchema": {
"type": "object",
"properties": {
"path": {
"type": "string",
"description": "Base directory to search from"
},
"pattern": {
"type": "string",
"description": "Search pattern (glob format)"
},
"excludePatterns": {
"type": "array",
"items": {
"type": "string"
},
"description": "Patterns to exclude from search (glob format)"
}
},
"required": ["path", "pattern"]
}
}
📄 Example Usage
Image Generation Examples
// Generate a 3D cartoon
{
"name": "generate_3d_cartoon",
"arguments": {
"prompt": "A friendly robot playing with a cat",
"fileName": "robot_cat_play"
}
}
File System Examples
// Read a file
{
"name": "read_file",
"arguments": {
"path": "C:/Users/YourUsername/Documents/example.txt"
}
}
// Write a file
{
"name": "write_file",
"arguments": {
"path": "C:/Users/YourUsername/Documents/new-file.txt",
"content": "This is the content of the file."
}
}
// List directory contents
{
"name": "list_directory",
"arguments": {
"path": "C:/Users/YourUsername/Documents"
}
}
// Create a directory
{
"name": "create_directory",
"arguments": {
"path": "C:/Users/YourUsername/Documents/new-folder"
}
}
// Search for files
{
"name": "search_files",
"arguments": {
"path": "C:/Users/YourUsername/Documents",
"pattern": "*.txt",
"excludePatterns": ["temp*", "*.tmp"]
}
}
🔒 Security Features
The server implements several security measures:
- Path Validation: All file paths are validated to ensure they are within allowed directories.
- Allowed Directories: Only directories explicitly set in the
ALLOWED_DIRECTORIESenvironment variable can be accessed. - Symlink Protection: Prevents access to directories outside the allowed scope via symlinks.
- Controlled Logging: Debug logs are disabled by default to prevent information leakage.
⚙️ Configuration Options
Environment Variables
| Variable | Description | Default |
|---|---|---|
GEMINI_API_KEY |
Google Gemini API key for image generation | (Required) |
ALLOWED_DIRECTORIES |
Comma-separated list of allowed file system paths | User's home dir, current dir |
IS_REMOTE |
Run in remote mode without browser opening | false |
SAVE_TO_DESKTOP |
Force saving to desktop directory | false |
DETECT_OS_PATHS |
Enable OS-specific path detection | true |
DEBUG |
Enable verbose debug logging | false |
🛠️ Troubleshooting
Common Issues:
-
JSON Parsing Errors in Claude:
- Ensure
DEBUGis set to "false" to prevent logs from interfering with JSON communication - Check for proper JSON formatting in the Claude configuration
- Ensure
-
File Access Denied:
- Verify that the paths you're trying to access are included in
ALLOWED_DIRECTORIES - Check file permissions on the target files/directories
- Verify that the paths you're trying to access are included in
-
Images Not Saving:
- Set
SAVE_TO_DESKTOPto "true" to ensure images save to the desktop - Check desktop path detection in the server logs (enable DEBUG temporarily)
- Set
📄 License
🤝 Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。