Enables execution of Git commands within a sandboxed workspace for version control operations like commits, branches, and repository management.
Enables execution of Jupyter commands for notebook-based data science and analysis workflows.
Enables execution of Node.js commands and scripts within the sandboxed workspace environment.
Allows running npm commands for package management, installation, and script execution in Node.js projects within the workspace.
Provides integration with Ollama models through compatible MCP clients for AI-assisted development workflows.
Allows running Python commands and scripts within the workspace for Python project development and execution.
Allows running Yarn commands for package management and script execution in JavaScript/Node.js projects.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP Workspace Serverlist all files in my workspace directory"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
🏆 ULTIMATE MCP Workspace Server
The Most Comprehensive MCP Server Ever Created - 36 professional tools across 15+ categories for development, DevOps, data processing, and automation. Transform Claude Desktop into the ultimate development environment!
🌟 Ultimate Features
🏆 36 Comprehensive Tools: The most complete MCP server available
🔒 Enterprise Security: Military-grade sandboxing and path validation
🚀 15+ Categories: File ops, Git, Docker, cloud storage, databases, and more
🌐 Multi-Platform: Windows, macOS, and Linux support
☁️ Multi-Cloud: AWS S3, Google Cloud, Azure integration
🐳 DevOps Ready: Docker management, package managers, CI/CD tools
📊 Data Processing: CSV, JSON, databases, web scraping, image processing
🔐 Security Suite: Encryption, hashing, secure key generation
⏰ Automation: Task scheduling, notifications, webhooks
🎨 Code Quality: Formatting, linting, analysis tools
✅ Production Ready: 109+ passing tests, comprehensive error handling
📋 Table of Contents
🚀 Installation
Prerequisites
Node.js v18 or higher (Download)
npm (comes with Node.js)
An MCP-compatible client (Claude Desktop, Cline, etc.)
Setup Steps
Clone the repository
git clone https://github.com/ShayYeffet/ultimate_mcp_server.git cd ultimate_mcp_serverInstall dependencies
npm installBuild the project
npm run buildVerify installation
npm test
You should see all 109 tests passing! ✅
⚡ Quick Start
For Claude Desktop Users
Find your Claude config file:
Windows:
%APPDATA%\Claude\claude_desktop_config.jsonmacOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonLinux:
~/.config/Claude/claude_desktop_config.json
Create or edit the file with this configuration:
{ "mcpServers": { "workspace": { "command": "node", "args": ["/ABSOLUTE/PATH/TO/ultimate_mcp_server/dist/index.js"], "env": { "MCP_WORKSPACE_ROOT": "/path/to/your/project", "MCP_ALLOWED_COMMANDS": "npm,git,node", "MCP_LOG_LEVEL": "info" } } } }Restart Claude Desktop
Test it! Ask Claude:
"List all files in my workspace" "Create a new file called test.txt with 'Hello World'"
⚙️ Configuration Guide
🔧 What You MUST Change
When setting up the MCP server, you must customize these values in your config file:
1. Path to the Server (Required)
Replace with:
Windows:
"C:\\Users\\YourName\\path\\to\\ultimate_mcp_server\\dist\\index.js"macOS/Linux:
"/home/username/path/to/ultimate_mcp_server/dist/index.js"
How to find it:
2. Workspace Root Directory (Required)
This is THE MOST IMPORTANT setting! This directory is where the AI can read/write files.
Examples:
Your web project:
"C:\\Users\\YourName\\projects\\my-website"Your app:
"/home/username/projects/my-app"A test folder:
"C:\\Users\\YourName\\ai-workspace"
⚠️ Security Note: The AI can ONLY access files inside this directory. Choose carefully!
3. Allowed Commands (Recommended)
Customize based on your needs:
Web development:
"npm,git,node,yarn"Python projects:
"python,pip,git"No commands:
""(empty string - disables command execution)Multiple commands:
"npm,git,python,node,cargo,go"
⚠️ Security Note: Only list commands you trust the AI to run!
📝 Optional Configuration
Read-Only Mode
Prevent ALL write operations (useful for analysis only):
Logging Level
Control how much logging you see:
Command Timeout
Set maximum time for commands (in milliseconds):
📋 Complete Configuration Examples
Example 1: Web Development Project
Example 2: Python Data Science Project
Example 3: Read-Only Code Review
Example 4: Multiple Workspaces
You can configure multiple MCP servers for different projects:
🛠️ Ultimate Tool Arsenal - 36 Tools
📁 Core File Operations (7 Tools)
list_files - List directory contents with filtering and sorting
read_file - Read file contents with encoding support
write_file - Create or update files atomically
delete_file - Delete files or directories safely
create_folder - Create directories with parent creation
apply_patch - Apply unified diff patches to files
run_command - Execute shell commands securely
🔍 Advanced File Operations (5 Tools)
search_files - Grep-like text search across files with patterns
find_files - Find files by name, pattern, size, date, extension
copy_file - Copy files and directories recursively
move_file - Move or rename files and folders
get_file_info - Detailed file metadata, checksums, permissions
📦 Archive & Compression (2 Tools)
compress_files - Create ZIP/TAR/GZ archives with compression
extract_archive - Extract compressed archives safely
🌐 Network Operations (1 Tool)
http_request - Full HTTP client with all methods, headers, timeouts
🔧 Git Operations (4 Tools)
git_status - Repository status, changes, branch information
git_diff - Show differences between commits, branches, files
git_log - View commit history with filters and formatting
git_branch - Branch management, creation, deletion, listing
💻 System Operations (3 Tools)
system_info - CPU, memory, disk, network, OS information
list_processes - Show running processes with resource usage
kill_process - Terminate processes by PID or name
🗄️ Database Operations (1 Tool)
database_query - Execute SQL queries on SQLite databases
🖼️ Image Processing (1 Tool)
image_process - Resize, crop, rotate, convert image formats
📄 PDF Manipulation (1 Tool)
pdf_manipulate - Extract text, get info, merge, split PDFs
🔐 Encryption & Security (1 Tool)
encrypt_decrypt - AES-256 encryption, hashing (SHA-256/512, MD5), key generation
⏰ Task Scheduling (1 Tool)
schedule_task - Schedule commands with cron/Windows Task Scheduler
📢 Notifications (1 Tool)
send_notification - System notifications, webhooks, email alerts
📝 Text Processing (1 Tool)
text_process - Analyze, transform, extract patterns, compare, generate text
📊 Data Processing (2 Tools)
csv_process - Read, write, transform, analyze, filter, merge, split CSV files
json_process - Parse, validate, transform, merge, extract, minify, prettify JSON
🕷️ Web Scraping (1 Tool)
web_scrape - Fetch HTML, extract elements, links, images, text, metadata
🐳 Docker Management (1 Tool)
docker_manage - Manage containers, images, networks, volumes, logs, exec
☁️ Cloud Storage (1 Tool)
cloud_storage - Upload, download, list, delete files on AWS S3, GCP, Azure
📦 Package Management (1 Tool)
package_manager - Install, uninstall, update packages with npm, yarn, pip, composer, gem, cargo, go
🎨 Code Formatting (1 Tool)
code_format - Format, lint, analyze, fix code with prettier, eslint, black, etc.
💡 Example Commands
Development Workflow
System Administration
Data & Content Processing
Cloud & DevOps
🔒 Security
Sandboxing
All file operations are strictly sandboxed to the MCP_WORKSPACE_ROOT directory:
✅ Allowed:
❌ Blocked:
Protection Mechanisms
Path Resolution: All paths resolved to absolute paths and validated
Boundary Checking: Resolved paths must start with workspace root
Traversal Detection:
../sequences that escape workspace are blockedAbsolute Path Blocking: Absolute paths outside workspace rejected
Symbolic Link Resolution: Symlinks resolved and validated
Command Allowlist: Only explicitly allowed commands can execute
Argument Safety: Command arguments passed as arrays (no shell injection)
Best Practices
✅ Use a dedicated workspace directory for AI operations
✅ Only allow commands you trust
✅ Use read-only mode for code review/analysis
✅ Regularly review what the AI is doing
✅ Keep the workspace separate from system directories
❌ Don't set workspace root to
/orC:\❌ Don't allow dangerous commands like
rm,del,format
🧪 Testing
The project includes comprehensive test coverage:
Test Structure
Unit Tests: Test individual functions and modules (26 tests)
Property-Based Tests: Use fast-check to verify properties across random inputs (83 tests)
Integration Tests: Test full MCP protocol communication
All 109 tests validate the correctness properties defined in the design specification.
🐛 Troubleshooting
Server Won't Start
Problem: Claude/Cline shows connection errors
Solutions:
Verify Node.js is installed:
node --version(should be 18+)Check the server path in config is correct and absolute
Ensure the project is built:
npm run buildCheck that
dist/index.jsexists
Security Errors
Problem: "Path outside workspace" errors
Solutions:
Ensure
MCP_WORKSPACE_ROOTis an absolute pathUse relative paths in requests (no leading
/)Avoid
../to navigate outside workspaceCheck for symbolic links pointing outside workspace
Command Not Allowed
Problem: "Command not allowed" errors
Solutions:
Add command to
MCP_ALLOWED_COMMANDS:"npm,git,python"Use only the command name, not full path
Ensure commands are comma-separated without spaces
Command Timeout
Problem: Commands killed before completing
Solutions:
Increase
MCP_COMMAND_TIMEOUT(value in milliseconds)For long builds:
"MCP_COMMAND_TIMEOUT": "1800000"(30 min)Check if command is actually hanging
File Not Found
Problem: AI can't find files that exist
Solutions:
Verify
MCP_WORKSPACE_ROOTpoints to correct directoryUse relative paths from workspace root
Check file actually exists:
lsordirin workspace
JSON Parse Error (Claude Desktop)
Problem: "Could not load app settings" or "invalid JSON"
Solutions:
Validate JSON syntax at jsonlint.com
Ensure all paths use double backslashes on Windows:
C:\\Users\\...Check for trailing commas (not allowed in JSON)
Verify file encoding is UTF-8 without BOM
📚 Environment Variables Reference
Variable | Type | Default | Description |
| string |
| REQUIRED: Absolute path to workspace directory |
| string |
| Comma-separated list of allowed commands |
| boolean |
| Disable all write operations |
| string |
| Logging level: debug, info, warn, error |
| number |
| Command timeout in milliseconds (5 min default) |
🤝 Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Development Setup
Fork the repository
Clone your fork
Install dependencies:
npm installMake your changes
Run tests:
npm testBuild:
npm run buildSubmit a PR
Guidelines
Ensure all tests pass
Add tests for new features
Follow TypeScript strict mode
Update documentation as needed
📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
🙏 Acknowledgments
Built following the Model Context Protocol specification
Tested with fast-check for property-based testing
Inspired by the need for secure AI-filesystem interaction
📞 Support
Issues: GitHub Issues
⭐ If you find this project useful, please consider giving it a star on GitHub!