Local File Organizer
A file organization MCP server that safely categorizes and manages files in allowed directories by type, with search and analysis capabilities.
README
Local File Organizer
A Python-based file organization system that leverages the Model Context Protocol (MCP) to safely organize and manage files across directories.
Overview
This project implements a file organization system using the Model Context Protocol (MCP) framework to:
- Safely access user-specified directories through robust permission checking
- Automatically organize files by type into categorized directories
- Search for files across allowed directories
- Analyze directory contents and provide detailed file information
Key Features
- Directory Security: Only operates on explicitly allowed directories
- Smart Categorization: Organizes files by extension into categories:
- Documents (PDF, DOC, DOCX, TXT, RTF, MD, HTML, JSON, CSV, etc.)
- Images (JPG, PNG, GIF, SVG, WEBP, HEIC, etc.)
- Videos (MP4, MOV, AVI, MKV, etc.)
- Audio (MP3, WAV, OGG, FLAC, etc.)
- Archives (ZIP, RAR, 7Z, TAR, etc.)
- Code (PY, JS, HTML, CSS, Java, etc.)
- Applications (DMG, EXE, MSI, etc.)
- Others (uncategorized file types)
- Project Detection: Identifies project directories to avoid disrupting code repositories
- Recursive Processing: Can analyze and organize nested directory structures
- Resource-Efficient: Optimized for performance with large directory structures
- Detailed Analytics: Provides insights into file distribution by type
Installation
# Clone the repository
git clone https://github.com/diganto-deb/local_file_organizer.git
cd local_file_organizer
# Install requirements
pip install -r requirements.txt
Usage
1. Configure Allowed Directories
Create or modify the .cursor/mcp.json file in your project directory:
{
"mcpServers": {
"filesystem": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-filesystem",
"/path/to/organize/dir1",
"/path/to/organize/dir2"
]
}
}
}
Replace the paths with the directories you want to allow the MCP server to access.
2. Enable the MCP Server
After configuring the .cursor/mcp.json file:
- Restart Cursor
- Open Cursor Settings (⚙️)
- Navigate to
MCP - You should see the
filesystemserver in the list of MCP servers- The server should appear with the name "filesystem" .
- Enable it by clicking the toggle switch next to the server name
3. Use File Organization Commands
Once the MCP server is enabled, you can use the file organization commands directly in Cursor's Agent:
# List all available categories
list_categories
# Analyze a directory without making changes
analyze_directory /path/to/directory
# Create category folders in a target directory
create_category_directories /path/to/target
# Organize files by type
organize_files /path/to/directory
# Search for files
search_files /path/to/directory "*.jpg"
Technical Implementation
The system uses:
- MCP Python SDK: For the core server implementation
- Filesystem MCP Server: For secure file operations
- Pathlib: For cross-platform path handling
- Type Annotations: For improved code quality and IDE support
Planned Features
The following features are planned for upcoming releases:
- File Write and Edit Functionality: Add capabilities to:
- Modify file contents directly
- Create new files with templates
- Batch rename files using patterns
- Edit file metadata
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
License
This project is licensed under the MIT License - see the LICENSE file for details.
Acknowledgments
- Model Context Protocol (MCP) Team
- Cursor IDE for MCP integration
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。