gabrielmaialva33 mcp filesystem

gabrielmaialva33 mcp filesystem avatar

by gabrielmaialva33

A secure Model Context Protocol (MCP) server providing filesystem access within predefined directories

What is gabrielmaialva33 mcp filesystem

:bookmark: 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.

:computer: Technologies

:wrench: Tools

:package: Installation

:heavy_check_mark: Prerequisites

The following software must be installed:

:arrow_down: Cloning the repository

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

:arrow_forward: 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

:gear: 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:

Using Local Installation (Recommended)

{
  "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.

:sparkles: 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
  }
}

:writing_hand: Author

Gabriel Maia
Gabriel Maia

License

MIT License

Leave a Comment

Frequently Asked Questions

What is MCP?

MCP (Model Context Protocol) is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI applications, providing a standardized way to connect AI models to different data sources and tools.

What are MCP Servers?

MCP Servers are lightweight programs that expose specific capabilities through the standardized Model Context Protocol. They act as bridges between LLMs like Claude and various data sources or services, allowing secure access to files, databases, APIs, and other resources.

How do MCP Servers work?

MCP Servers follow a client-server architecture where a host application (like Claude Desktop) connects to multiple servers. Each server provides specific functionality through standardized endpoints and protocols, enabling Claude to access data and perform actions through the standardized protocol.

Are MCP Servers secure?

Yes, MCP Servers are designed with security in mind. They run locally with explicit configuration and permissions, require user approval for actions, and include built-in security features to prevent unauthorized access and ensure data privacy.

Related MCP Servers

Filesystem MCP Server avatar

Filesystem MCP Server

A core MCP server that provides filesystem access capabilities for Claude. Enables secure reading, writing, and management of files on your local system with granular permission controls.

filesystemcoreofficial
chrisdoc hevy mcp avatar

chrisdoc hevy mcp

mcp
sylphlab pdf reader mcp avatar

sylphlab pdf reader mcp

An MCP server built with Node.js/TypeScript that allows AI agents to securely read PDF files (local or URL) and extract text, metadata, or page counts. Uses pdf-parse.

pdf-parsetypescriptnodejs
aashari mcp server atlassian bitbucket avatar

aashari mcp server atlassian bitbucket

Node.js/TypeScript MCP server for Atlassian Bitbucket. Enables AI systems (LLMs) to interact with workspaces, repositories, and pull requests via tools (list, get, comment, search). Connects AI directly to version control workflows through the standard MCP interface.

atlassianrepositorymcp
aashari mcp server atlassian confluence avatar

aashari mcp server atlassian confluence

Node.js/TypeScript MCP server for Atlassian Confluence. Provides tools enabling AI systems (LLMs) to list/get spaces & pages (content formatted as Markdown) and search via CQL. Connects AI seamlessly to Confluence knowledge bases using the standard MCP interface.

atlassianmcpconfluence
prisma prisma avatar

prisma prisma

Next-generation ORM for Node.js & TypeScript | PostgreSQL, MySQL, MariaDB, SQL Server, SQLite, MongoDB and CockroachDB

cockroachdbgomcp
Zzzccs123 mcp sentry avatar

Zzzccs123 mcp sentry

mcp sentry for typescript sdk

mcptypescript
zhuzhoulin dify mcp server avatar

zhuzhoulin dify mcp server

mcp
zhongmingyuan mcp my mac avatar

zhongmingyuan mcp my mac

mcp
zhixiaoqiang desktop image manager mcp avatar

zhixiaoqiang desktop image manager mcp

MCP 服务器,用于管理桌面图片、查看详情、压缩、移动等(完全让Trae实现)

mcp

Submit Your MCP Server

Share your MCP server with the community

Submit Now