Frequently Asked Questions
Find answers to common questions about Claude Code, Computer Use, and MCP
Claude Code
Is Claude Code free to use?
Claude Code is currently in beta as a research preview. Typical usage costs range from $5-10 per developer per day, though intensive use can exceed $100 per hour.
Where can I try Claude Code?
You can experience Claude's capabilities at claude.ai. For Claude Code specifically, join the waitlist at the Anthropic Console.
What programming languages are supported?
Claude Code can work with any programming language and understands various development tools and frameworks.
What's the learning curve?
Claude Code uses natural language, so you can start being productive immediately without learning complex commands.
Do I need special hardware?
Minimal requirements include 4GB RAM and Node.js 18+. Computer Use features work best in a containerized environment.
Can I use it in my company?
Yes, Claude Code is suitable for both personal and commercial use. Many companies use it for development workflows.
Computer Use
How does Computer Use work?
Computer Use runs in a sandboxed environment where Claude can interact with applications through a virtual display, ensuring safety and security.
Is it safe to use?
Yes, Computer Use operates in a secure sandbox with strict permissions. All actions are logged and can be reviewed or revoked at any time.
What can I automate with Computer Use?
You can automate UI testing, application workflows, data entry tasks, and any desktop interaction that follows predictable patterns.
What operating systems are supported?
Computer Use is available for Windows, macOS, and Linux. The experience and capabilities are consistent across all platforms.
Model Context Protocol (MCP)
What is MCP?
MCP 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, enabling Claude to interact with various data sources and services securely.
How do MCP Servers work?
MCP Servers follow a client-server architecture where Claude Desktop connects to multiple servers. Each server provides specific functionality through standardized endpoints and protocols.
Can I create my own MCP server?
Yes, you can develop and submit your own MCP servers through our GitHub open source project. Your contribution will help expand the ecosystem for all developers.
Support & Privacy
Is support available?
Yes, you can report issues using the /bug command, through GitHub, or get help in our developer community.
What about data privacy?
We do not train models on your code or feedback. User feedback transcripts are stored for only 30 days with strict access controls.