MCP Catalogs
Home

filesystem vs open-computer-use

Side-by-side comparison to help you pick between these two MCP servers.

filesystem
by modelcontextprotocol
open-computer-use
by Wide-Moat
Stars★ 85,748★ 74
30d uses
Score7749
Official
Categories
File SystemDeveloper ToolsProductivity
Developer ToolsProductivityAI / LLM Tools
LanguageTypeScriptPython
Last committhis monththis month

filesystem · Summary

A feature-rich MCP server for filesystem operations with dynamic directory access control.

open-computer-use · Summary

MCP server providing Docker workspaces with browser, terminal, code execution and document skills for any LLM.

filesystem · Use cases

  • Enable AI models to read and write project files during development
  • Allow Claude or other MCP clients to browse and analyze codebases
  • Provide secure sandboxed access to specific directories for content generation

open-computer-use · Use cases

  • AI agent web scraping and data analysis with real-time browser interaction
  • Automated document generation (Word, Excel, PDF) with professional formatting
  • Code development and testing in isolated environments with full terminal access

filesystem · Install

Installation

Using NPX

{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-filesystem",
        "/path/to/allowed/directory"
      ]
    }
  }
}

Using Docker

{
  "mcpServers": {
    "filesystem": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "--mount", "type=bind,src=/path/to/allowed/dir,dst=/projects/allowed/dir",
        "mcp/filesystem",
        "/projects"
      ]
    }
  }
}

VS Code Extension

Click the installation buttons in the README to install directly in VS Code.

open-computer-use · Install

Installation

git clone https://github.com/Wide-Moat/open-computer-use.git
cd open-computer-use
cp .env.example .env
# Edit .env — set OPENAI_API_KEY (or any OpenAI-compatible provider)

# 1. Start Computer Use Server (builds workspace image on first run, ~15 min)
docker compose up --build

# 2. Start Open WebUI (in another terminal)
docker compose -f docker-compose.webui.yml up --build

For MCP client integration, connect to http://localhost:8081/mcp for self-hosted or https://api.yambr.com/mcp/computer_use with API key for hosted version.

Comparison generated from public README + GitHub signals. Last updated automatically.