Computer Use AI SDK
@m13v
About Computer Use AI SDK
No overview available yet
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"MCP-server-client-computer-use-ai-sdk": {
"command": "npx",
"args": [
"tsx",
"main.ts"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Computer Use AI SDK?
It is an open‑source MCP server that controls a computer natively on macOS, using underlying desktop‑rendered elements instead of pixel‑based vision. It is designed as an alternative to proprietary computer‑use agents like OpenAI’s Operator and Claude’s Computer Use, giving developers full control without virtual machines or guardrails.
How to use Computer Use AI SDK?
Clone the repository, install Rust and Node.js, then run the backend server with cargo run --bin server in the mcp-server-os-level directory. Choose between a CLI interface (set the ANTHROPIC_API_KEY environment variable and run npx tsx main.ts in mcp-client-cli-interface) or a web‑app interface (set the key in a .env file and run npm run dev in mcp-client-nextjs).
Key features of Computer Use AI SDK
- Launches apps, reads content, clicks, enters text, and presses keys.
- Uses desktop‑rendered elements for speed and reliability.
- Native on macOS with no virtual machine overhead.
- No guardrails — full control over any app or website.
- Provides both CLI and web‑based client interfaces.
- Integrates with Anthropic’s API for AI agent capabilities.
Use cases of Computer Use AI SDK
- Build custom AI agent workflows for automating everyday computer tasks.
- Develop custom user interfaces for computer automation.
- Schedule workflows to run periodically via cron.
- Combine with other MCP servers for cross‑system automation.
FAQ from Computer Use AI SDK
What makes this different from pixel‑based computer use tools?
It reads desktop‑rendered elements instead of pixels, making it faster and more reliable than vision‑based models, and runs natively on macOS without virtual machines.
What are the runtime requirements?
You need Rust (install via rustup), Node.js and npm, and an Anthropic API key set as an environment variable.
Does it work on Windows or Linux?
The README only describes native macOS support; no other platforms are mentioned.
How do I authenticate?
Set the ANTHROPIC_API_KEY environment variable (or place it in a .env file for the web app) with your Anthropic API key.
Are there any guardrails or restrictions?
No guardrails — the tool is designed for full control of your computer, and you can use it with any app or website however you want.
Frequently asked questions
What makes this different from pixel‑based computer use tools?
It reads desktop‑rendered elements instead of pixels, making it faster and more reliable than vision‑based models, and runs natively on macOS without virtual machines.
What are the runtime requirements?
You need Rust (install via rustup), Node.js and npm, and an Anthropic API key set as an environment variable.
Does it work on Windows or Linux?
The README only describes native macOS support; no other platforms are mentioned.
How do I authenticate?
Set the `ANTHROPIC_API_KEY` environment variable (or place it in a `.env` file for the web app) with your Anthropic API key.
Are there any guardrails or restrictions?
No guardrails — the tool is designed for full control of your computer, and you can use it with any app or website however you want.
Basic information
More Developer Tools MCP servers
endoflife.ai
endoflife.aiFree MCP server for software end-of-life intelligence: EOL dates, support status, and the 0-100 EOL Risk Score across 485 tracked products. Agents can check a single version, pull a product's full lifecycle schedule, or
MCP Containers
metorialConnect any AI model to 1200+ integrations (MCP, CLI, API)
DevDocs by CyberAGI 🚀
cyberagiincCompletely free, private, UI based Tech Documentation MCP server. Designed for coders and software developers in mind. Easily integrate into Cursor, Windsurf, Cline, Roo Code, Claude Desktop App
MCP Unity Editor (Game Engine)
CoderGamesterModel Context Protocol (MCP) plugin to connect with Unity Editor — designed for Cursor, Claude Code, Codex, Windsurf and other IDEs
Comments