Skip to main content
Glama

MCP Filesystem Server

A comprehensive Model Context Protocol (MCP) server providing advanced filesystem operations with intelligent features for AI-assisted development workflows.

Features

🔧 Core Tools

  • batch_read - Read multiple files efficiently in a single operation

  • rename_file - Rename files with safety checks

  • move_file - Move files with automatic directory creation

  • check_structure - Display project structure with smart filtering

  • run_command - Execute commands with Python virtual environment auto-activation

🚀 Advanced Capabilities

  • Smart Virtual Environment Detection - Automatically activates Python .venv when detected

  • Cross-Platform Support - Works on Windows, macOS, and Linux

  • Intelligent Filtering - Uses .checkignore files + built-in patterns for clean structure views

  • Command Prohibition - Prevents file management command overlap between tools

  • Enhanced Quote Handling - Proper execution of complex commands with quoted arguments

  • Clean Output Format - Focused, minimal output for better AI integration

Related MCP server: Filesystem MCP Server

Quick Start

Installation

npm install
npm run build

Configuration

Create .cursor/mcp.json in your project:

{
  "mcpServers": {
    "filesystem": {
      "command": "node",
      "args": [
        "/absolute/path/to/dist/index.js"
      ],
      "env": {}
    }
  }
}

Tool Documentation

📄 batch_read

Read multiple files concurrently with automatic encoding detection.

{
  projectPath: "C:/project",
  relativePaths: ["src/index.ts", "package.json", "README.md"]
}

Features:

  • Concurrent file reading for performance

  • UTF-8 and binary (base64) support

  • Empty file detection ([EMPTY] indicator)

  • Graceful error handling for missing files

🔄 rename_file

Safely rename files with conflict detection.

{
  projectPath: "C:/project", 
  currentPath: "src/oldname.js",
  newName: "newname.js"
}

Safety Features:

  • Source file existence validation

  • Destination conflict prevention

  • Clear success/error feedback

📁 move_file

Move files with automatic directory creation.

{
  projectPath: "C:/project",
  sourcePath: "src/component.tsx", 
  destinationPath: "src/components/component.tsx"
}

Features:

  • Automatic parent directory creation

  • Conflict detection and prevention

  • Cross-directory moves

🌳 check_structure

Display clean project structure with intelligent filtering.

{
  projectPath: "C:/project"
}

Smart Filtering:

  • Built-in ignore patterns (node_modules, .git, dist, etc.)

  • Custom .checkignore file support

  • Empty directory detection

  • Clean tree visualization

.checkignore Format

# Comments start with #
temp/
*.tmp
*.log
debug/

💻 run_command

Execute development commands with Python virtual environment auto-activation.

{
  projectPath: "C:/project",
  command: "npm test"
}

Features:

  • Auto venv activation - Detects .venv and activates automatically

  • Cross-platform - Windows and Unix support

  • Quote handling - Proper execution of complex quoted commands

  • Command prohibition - Blocks file management commands (use dedicated tools)

Prohibited Commands:

  • File reading: cat, type, more, etc. → Use batch_read

  • File moving: mv, move, ren → Use rename_file/move_file

  • File listing: dir, ls, tree → Use check_structure

Examples

Python Development Workflow

// Check project structure
{ projectPath: "C:/python-project" }

// Read configuration files  
{
  projectPath: "C:/python-project",
  relativePaths: ["requirements.txt", "setup.py", "src/main.py"]
}

// Run tests (auto-activates .venv)
{
  projectPath: "C:/python-project", 
  command: "pytest tests/ -v"
}

// Install packages (in venv)
{
  projectPath: "C:/python-project",
  command: "pip install requests"
}

Node.js Development Workflow

// Build project
{
  projectPath: "C:/node-project",
  command: "npm run build"
}

// Run tests
{
  projectPath: "C:/node-project", 
  command: "npm test"
}

// Lint code
{
  projectPath: "C:/node-project",
  command: "npx eslint src/ --fix"
}

Technical Details

Virtual Environment Detection

The server automatically detects Python virtual environments:

  • Windows: .venv\Scripts\activate.bat

  • Unix/Linux: .venv/bin/activate

When detected, all Python commands are executed within the virtual environment context.

Error Handling

All tools provide comprehensive error handling:

  • File not found - Clear error messages with full paths

  • Permission denied - Specific access error reporting

  • Command failures - Exit codes and stderr capture

  • Validation errors - Pre-execution checks prevent issues

Performance

  • Concurrent operations - Multiple files read simultaneously

  • Smart filtering - Reduces unnecessary filesystem traversal

  • Efficient command execution - Minimal overhead for command operations

Development

Building

npm run build

Testing

npm run dev  # Build and start

Project Structure

src/
├── index.ts          # Main MCP server implementation
package.json          # Dependencies and scripts
tsconfig.json         # TypeScript configuration
.checkignore          # Structure filtering patterns
README.md            # This documentation

License

MIT License

Contributing

Contributions welcome! Please ensure all tools maintain the clean, focused output format and comprehensive error handling standards.

A
license - permissive license
-
quality - not tested
C
maintenance

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ceciliomichael/mcp-filesystem'

If you have feedback or need assistance with the MCP directory API, please join our Discord server