SylphxAI/filesystem-mcp

Filesystem MCP 📁

Secure filesystem operations for AI agents - Token-optimized with batch processing

Batch operations • Project root safety • Token optimized • Zod validation

Quick Start • Installation • Tools

🚀 Overview

Empower your AI agents (like Claude/Cline) with secure, efficient, and token-saving access to your project files. This Node.js server implements the Model Context Protocol (MCP) to provide a robust set of filesystem tools.

The Problem:

Traditional AI filesystem access:
- Shell commands for each operation ❌
- No batch processing (high token cost) ❌
- Unsafe (no project root boundaries) ❌
- High latency (shell spawn overhead) ❌

The Solution:

Filesystem MCP Server:
- Batch operations (10+ files at once) ✅
- Token optimized (reduce round trips) ✅
- Secure (confined to project root) ✅
- Direct API (no shell overhead) ✅

Result: Safe, fast, and token-efficient filesystem operations for AI agents.

⚡ Performance Advantages

Token & Latency Optimization

Real-World Benefits

• Batch file reads - Read 10 files in one request vs 10 requests
• Multi-file edits - Edit multiple files with single tool call
• Recursive operations - List entire directory trees efficiently
• Detailed status - Per-item success/failure reporting

🎯 Why Choose This Server?

Security & Safety

• 🛡️ Project Root Confinement - All operations restricted to cwd at launch
• 🔒 Permission Control - Built-in chmod/chown tools
• ✅ Validation - Zod schemas validate all arguments
• 🚫 Path Traversal Prevention - Cannot escape project directory

Efficiency & Performance

• ⚡ Batch Processing - Process multiple files/directories per request
• 🎯 Token Optimized - Reduce AI-server communication overhead
• 🚀 Direct API - No shell process spawning
• 📊 Detailed Results - Per-item status for batch operations

Developer Experience

• 🔧 Easy Setup - npx/bunx for instant use
• 🐳 Docker Ready - Official Docker image available
• 📦 Comprehensive Tools - 11+ filesystem operations
• 🔄 MCP Standard - Full protocol compliance

📦 Installation

Method 1: npx/bunx (Recommended)

The simplest way - always uses latest version from npm.

Using npx:

{
  "mcpServers": {
    "filesystem-mcp": {
      "command": "npx",
      "args": ["@sylphlab/filesystem-mcp"],
      "name": "Filesystem (npx)"
    }
  }
}

Using bunx:

{
  "mcpServers": {
    "filesystem-mcp": {
      "command": "bunx",
      "args": ["@sylphlab/filesystem-mcp"],
      "name": "Filesystem (bunx)"
    }
  }
}

Important: The server uses its own Current Working Directory (cwd) as the project root. Ensure your MCP host (e.g., Cline/VSCode) launches the command with cwd set to your project's root directory.

Method 2: Docker

Use the official Docker image for containerized environments.

{
  "mcpServers": {
    "filesystem-mcp": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-v",
        "/path/to/your/project:/app",
        "sylphlab/filesystem-mcp:latest"
      ],
      "name": "Filesystem (Docker)"
    }
  }
}

Remember to replace /path/to/your/project with your actual project path.

Method 3: Local Build (Development)

# Clone repository
git clone https://github.com/SylphxAI/filesystem-mcp.git
cd filesystem-mcp

# Install dependencies
pnpm install

# Build
pnpm run build

# Watch mode (auto-rebuild)
pnpm run dev

MCP Host Configuration:

{
  "mcpServers": {
    "filesystem-mcp": {
      "command": "node",
      "args": ["/path/to/filesystem-mcp/dist/index.js"],
      "name": "Filesystem (Local Build)"
    }
  }
}

🚀 Quick Start

Once configured in your MCP host (see Installation), your AI agent can immediately use the filesystem tools.

Example Agent Interaction

<use_mcp_tool>
  <server_name>filesystem-mcp</server_name>
  <tool_name>read_content</tool_name>
  <arguments>{"paths": ["src/index.ts", "package.json"]}</arguments>
</use_mcp_tool>

Server Response:

{
  "results": [
    {
      "path": "src/index.ts",
      "content": "...",
      "success": true
    },
    {
      "path": "package.json",
      "content": "...",
      "success": true
    }
  ]
}

📋 Features

File Operations

Directory Operations

Management Operations

Permission Operations

Key Benefit: Tools supporting batch operations process each item individually and return detailed per-item status reports.

💡 Design Philosophy

Core Principles

1. Security First

   • All operations confined to project root
   • Path traversal prevention
   • Permission controls built-in

2. Efficiency Focused

   • Batch processing reduces token usage
   • Direct API calls (no shell overhead)
   • Minimal communication round trips

3. Robustness

   • Per-item success/failure reporting
   • Detailed error messages
   • Zod schema validation

4. Simplicity

   • Clear, consistent API
   • MCP standard compliance
   • Easy integration

📊 Comparison with Alternatives

🛠️ Tech Stack

🎯 Use Cases

AI Agent Development

Enable AI agents to:

• Read project files - Access code, configs, docs
• Edit multiple files - Refactor across codebase
• Search codebases - Find patterns and definitions
• Manage project structure - Create, move, organize files

Code Assistants

Build powerful coding tools:

• Cline/Claude integration - Direct filesystem access
• Batch refactoring - Edit multiple files at once
• Safe operations - Confined to project directory
• Efficient operations - Reduce token costs

Automation & Scripting

Automate development tasks:

• File generation - Create boilerplate files
• Project setup - Initialize directory structures
• Batch processing - Handle multiple files efficiently
• Content transformation - Search and replace across files

🗺️ Roadmap

✅ Completed

• Core filesystem operations (read, write, edit, etc.)
• Batch processing for most tools
• Project root security
• Docker image
• npm package
• Zod validation

🚀 Planned

• File watching capabilities
• Streaming support for large files
• Advanced filtering for list_files
• Performance benchmarks
• Compression/decompression tools
• Symlink management

🤝 Contributing

Contributions are welcome! Please follow these guidelines:

1. Fork the repository
2. Create a feature branch - git checkout -b feature/my-feature
3. Write tests - Ensure good coverage
4. Follow TypeScript strict mode - Type safety first
5. Add documentation - Update README if needed
6. Submit a pull request

Development Setup

# Clone and install
git clone https://github.com/SylphxAI/filesystem-mcp.git
cd filesystem-mcp
pnpm install

# Build
pnpm run build

# Watch mode (auto-rebuild)
pnpm run dev

🤝 Support

• 🐛 Bug Reports
• 💬 Discussions
• 📧 Email

Show Your Support: ⭐ Star • 👀 Watch • 🐛 Report bugs • 💡 Suggest features • 🔀 Contribute

📄 License

MIT © Sylphx

🙏 Credits

Built with:

• Model Context Protocol - MCP standard
• Zod - Schema validation
• TypeScript - Type safety
• pnpm - Package manager

Special thanks to the MCP community ❤️

📚 Publishing

This repository uses GitHub Actions to automatically publish to:

• npm: @sylphlab/filesystem-mcp
• Docker Hub: sylphlab/filesystem-mcp

Triggered on version tags (v*.*.*) pushed to main branch.

Required secrets: NPM_TOKEN, DOCKERHUB_USERNAME, DOCKERHUB_TOKEN

Secure. Efficient. Token-optimized.
_{The filesystem MCP server that saves tokens and keeps your projects safe}

sylphx.com • @SylphxAI • hi@sylphx.com