A powerful Model Context Protocol (MCP) tool that enables AI assistants to capture and analyze screenshots using Claude Vision API. Take screenshots, analyze screen content, and get AI insights about your desktop interface.
- 📸 Instant full-screen screenshot capture
- 🔍 AI-powered scene analysis with Claude Vision
- 🤖 Seamless integration with MCP-compatible AI assistants
- 🛠️ Easy configuration and setup
- Capture and analyze screenshots of your desktop
- Analyze UI elements and layouts
- Debug visual issues with screen captures
- Get AI insights about screen content
- Document interface elements and layouts
- Screen recording and analysis
- Desktop automation with visual feedback
The easiest way to install Screen View MCP is through Smithery:
# For Claude Desktop
npx @smithery/cli install @hemenge133/screen-view-mcp --client claude --env.anthropicApiKey=your-api-key
# For Cursor
npx @smithery/cli install @hemenge133/screen-view-mcp --client cursor --env.anthropicApiKey=your-api-key
# For CLIne
npx @smithery/cli install @hemenge133/screen-view-mcp --client cline --env.anthropicApiKey=your-api-key
# For Windsurf
npx @smithery/cli install @hemenge133/screen-view-mcp --client windsurf --env.anthropicApiKey=your-api-key
You can also run it directly through Smithery:
npx @smithery/cli run @hemenge133/screen-view-mcp --env.anthropicApiKey=your-api-key
This will automatically:
- Install the package
- Configure your AI client
- Set up environment variables
- Install the package:
# Install the latest version
npm install -g screen-view-mcp
# To ensure you get the exact latest version and avoid caching issues
npm install -g screen-view-mcp@2.0.14 # Replace with latest version number
- Add to your AI client config file:
Claude Desktop:
- Windows:
%APPDATA%/Claude/claude_desktop_config.json
- MacOS:
~/Library/Application Support/Claude/claude_desktop_config.json
Cursor:
- Windows:
%APPDATA%/Cursor/mcp.json
- MacOS:
~/Library/Application Support/Cursor/mcp.json
CLIne:
~/.config/cline/mcp.json
Windsurf:
~/.config/windsurf/mcp.json
{
"mcpServers": {
"screen-view-mcp": {
"command": "npx",
"args": [
"screen-view-mcp@2.0.14" // Specify exact version to avoid caching issues
],
"transport": "stdio",
"env": {
"ANTHROPIC_API_KEY": "your-anthropic-api-key"
}
}
}
}
If you encounter problems with the npm installation (such as "Invalid file signature" errors):
- Try installing with an explicit version number:
npm install -g screen-view-mcp@2.0.14 # Replace with latest version number
- Clear npm cache and reinstall:
npm cache clean --force
npm install -g screen-view-mcp@2.0.14
- Install directly from a local tarball:
# Create a local package file
npm pack
# Install from the local file
npm install -g ./screen-view-mcp-2.0.14.tgz
Captures and analyzes the current screen content.
Parameters:
{
prompt?: string; // Custom prompt for analysis
modelName?: string; // Claude model to use
saveScreenshot?: boolean; // Save screenshot locally
}
Example usage in Claude:
Can you analyze what's on my screen right now and describe the layout?
- Clone and install:
git clone https://github.com/yourusername/screen-view-mcp.git
cd screen-view-mcp
npm install
- Build:
npm run build
- Test locally:
node dist/index.js --api-key=your-anthropic-api-key
MIT