Skip to main content
Glama

MCP Filesystem Server

by A-Niranjan

: About

MCP Filesystem Server provides secure filesystem access for AI models through the Model Context Protocol. It enforces strict path validation and only allows access to predefined directories.

: Technologies

: Tools

: Installation

: Prerequisites

The following software must be installed:

: Cloning the repository

$ git clone https://github.com/gabrielmaialva33/mcp-filesystem.git $ cd mcp-filesystem

: Running the application

Local Development
# Install dependencies $ pnpm install # Build the application $ pnpm build # Run the server (specify directory to allow access to) $ pnpm start /path/to/allowed/directory # Or use configuration file $ pnpm start --config=config.json
Using NPM Package
# Install globally $ npm install -g @gabrielmaialva33/mcp-filesystem # Run the server $ mcp-filesystem /path/to/allowed/directory # Or use with npx (no installation needed) $ npx @gabrielmaialva33/mcp-filesystem /path/to/allowed/directory # Create a sample configuration file $ npx @gabrielmaialva33/mcp-filesystem --create-config=config.json
Using Docker
# Build the Docker image $ docker build -t gabrielmaialva33/mcp-filesystem . # Run using Docker $ docker run -i --rm -v /path/to/data:/data:ro gabrielmaialva33/mcp-filesystem /data # Use with config file $ docker run -i --rm -v /path/to/config.json:/app/config.json -v /path/to/data:/data gabrielmaialva33/mcp-filesystem --config=/app/config.json
Using Docker Compose
# Create a data directory $ mkdir -p data # Start the server $ docker-compose up -d

: Usage

Using with Claude Desktop

Claude Desktop can be configured to use this MCP server for filesystem access. Add the following to your claude_desktop_config.json:

{ "mcpServers": { "filesystem": { "command": "mcp-filesystem", "args": [ "/Users/gabrielmaia/Documents", "/Users/gabrielmaia/Desktop", "/Users/gabrielmaia/Downloads" ] } } }

Make sure to make the executable available globally:

# Make the binary executable chmod +x /Users/gabrielmaia/.nvm/versions/node/v22.14.0/bin/mcp-filesystem
Using NPX
{ "mcpServers": { "filesystem": { "command": "npx", "args": [ "-y", "@gabrielmaialva33/mcp-filesystem", "/Users/username/Desktop", "/path/to/other/allowed/dir" ] } } }
Using Docker

Note: When using Docker, all directories must be mounted to /projects by default. Adding the ro flag will make the directory read-only.

{ "mcpServers": { "filesystem": { "command": "docker", "args": [ "run", "-i", "--rm", "--mount", "type=bind,src=/Users/username/Desktop,dst=/projects/Desktop", "--mount", "type=bind,src=/path/to/other/allowed/dir,dst=/projects/other/allowed/dir,ro", "--mount", "type=bind,src=/path/to/file.txt,dst=/projects/path/to/file.txt", "gabrielmaialva33/mcp-filesystem", "/projects" ] } } }

Available Tools

The MCP Filesystem Server provides these tools:

File System Operations
  • read_file: Read a file's content
  • read_multiple_files: Read multiple files at once
  • write_file: Create or overwrite a file
  • edit_file: Make precise edits with diff preview
  • create_directory: Create directories recursively
  • list_directory: List directory contents
  • directory_tree: Get a recursive tree view
  • move_file: Move or rename files
  • search_files: Find files matching patterns
  • get_file_info: Get file metadata
  • list_allowed_directories: See accessible directories
System & Network Operations
  • get_metrics: View server performance metrics (v0.3.0+)
  • execute_command: Execute system commands securely (v0.3.1+)
  • curl_request: Execute HTTP requests to external APIs (coming in v1.2.0)
Using curl_request Tool (Coming in v1.2.0)

The curl_request tool will allow you to make HTTP requests to external APIs:

// Example: Making a GET request with authentication curl_request({ url: 'https://api.example.com/data', method: 'GET', headers: { Authorization: 'Bearer your_token_here', }, }) // Example: POST request with JSON data curl_request({ url: 'https://api.example.com/create', method: 'POST', headers: { 'Content-Type': 'application/json', }, data: '{"name":"Example","value":123}', })

See the docs/curl-tool-examples.md file for more detailed examples.

: Features

Core Features

  • Secure Access: Strict path validation prevents unauthorized access
  • File Operations: Read, write, edit, and move files
  • Directory Operations: Create, list, get tree views, and search directories
  • Metadata Access: View file and directory information
  • Command Execution: Securely execute system commands with strict validation
  • Docker Support: Easy deployment with Docker and Docker Compose

New Features in v0.3.0

  • Structured Logging: Detailed logging with different levels (debug, info, warn, error)
  • Performance Metrics: Track operation counts, errors, and execution times
  • Configuration Management: Support for JSON configuration files
  • Path Caching: Improved performance for frequently accessed paths
  • Improved Error Handling: Specialized error types with structured information
  • File Size Validation: Prevent loading excessively large files
  • CLI Improvements: Help command, version info, and config generation

Configuration Options

You can create a configuration file using:

$ mcp-filesystem --create-config=config.json

Example configuration:

{ "allowedDirectories": ["/path/to/allowed/dir1", "/path/to/allowed/dir2"], "logLevel": "info", "logFile": "/path/to/logs/mcp-filesystem.log", "serverName": "secure-filesystem-server", "serverVersion": "0.3.0", "cache": { "enabled": true, "maxSize": 1000, "ttlMs": 60000 }, "metrics": { "enabled": true, "reportIntervalMs": 60000 }, "security": { "maxFileSize": 10485760, "allowSymlinks": true, "validateRealPath": true } }

: Author

License

MIT License

Deploy Server
-
security - not tested
A
license - permissive license
-
quality - not tested

hybrid server

The server is able to function both locally and remotely, depending on the configuration or use case.

Provides secure filesystem access for AI models through the Model Context Protocol with strict path validation, file operations, directory management, and system command execution within predefined directories.

  1. :computer: Technologies
    1. :wrench: Tools
      1. :package: Installation
        1. :heavy_check_mark: Prerequisites
        2. :arrow_down: Cloning the repository
        3. :arrow_forward: Running the application
      2. :gear: Usage
        1. Using with Claude Desktop
        2. Available Tools
      3. :sparkles: Features
        1. Core Features
        2. New Features in v0.3.0
        3. Configuration Options
        4. :writing_hand: Author
      4. License

        Related MCP Servers

        • A
          security
          F
          license
          A
          quality
          Enables AI models to perform file system operations (reading, creating, and listing files) on a local file system through a standardized Model Context Protocol interface.
          Last updated -
          3
        • -
          security
          A
          license
          -
          quality
          A Model Context Protocol (MCP) server that allows AI models to safely access and interact with local file systems, enabling reading file contents, listing directories, and retrieving file metadata.
          Last updated -
          9
          9
          MIT License
          • Linux
        • -
          security
          A
          license
          -
          quality
          A redesigned Model Context Protocol server that enables AI models to access filesystems through privacy-preserving path aliases with an optimized 6-function API interface.
          Last updated -
          MIT License
        • A
          security
          A
          license
          A
          quality
          A secure Model Context Protocol server that provides controlled filesystem access within predefined directories, enabling AI models to perform file and directory operations with strict path validation.
          Last updated -
          16
          4
          7
          MIT License
          • Linux
          • Apple

        View all related MCP servers

        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/A-Niranjan/mcp-filesystem'

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