About
nuphus-mcp connects MCP-compatible clients to desktop automation workflows.
Features
- Stdio Model Context Protocol server for desktop and browser automation
- Desktop tools for screenshots, windows, mouse, keyboard, clipboard, and semantic accessibility actions
- Browser tools for Chrome or Edge through Chrome DevTools Protocol
- Local OCR and optional YOLO icon detection for perception workflows
- BYOK vision integration for OpenAI-compatible or Anthropic-native vision models
Use Cases
AI agent builders
Add desktop automation actions to an MCP-compatible assistant.
Platform teams
Expose a controlled local or service-specific automation interface through MCP.
Developers testing tool-calling agents
Use documented tools and config examples to evaluate agent workflows.
What This Server Can Do
MCP servers expose three types of capabilities to AI clients. Here's what nuphus-mcp supports.
Tools
Supported45 toolsFunctions your AI client can call to perform actions — like querying a database, creating a file, or calling an API.
How to use: Tools run automatically when your AI client decides they're needed. Ask your AI assistant to perform a task, and it will invoke the right tool.
Resources
Not availableThis server does not expose read-only data resources.
Prompts
Not availableThis server does not provide pre-built prompt templates.
For the full list of available tools, resources, and prompts, check the README on GitHub.
Available Tools (2)
tools/listLists the MCP tools exposed by this server.
tools/callCalls one of the documented 45 server tools.