Enables AI assistants to view and analyze screenshots from React Native/Expo applications for AI-powered mobile UI development.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@ExpoSnap show me the latest screenshot from the login screen"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol (MCP) server that enables AI assistants to view and analyze screenshots from React Native/Expo applications. Seamlessly integrates with Claude, Cursor, VS Code, and other MCP-compatible editors for AI-powered mobile UI development.
Related MCP server: Screen View MCP
1. Add MCP server to your IDE
claude mcp add exposnap -- npx -y exposnapAdd to .cursor/mcp.json:
{
"mcpServers": {
"exposnap": {
"command": "npx",
"args": ["-y", "exposnap"]
}
}
}Add to .vscode/mcp.json:
{
"servers": {
"exposnap": {
"type": "stdio",
"command": "npx",
"args": ["-y", "exposnap"]
}
}
}Settings → Developer → Edit Config:
{
"mcpServers": {
"exposnap": {
"command": "npx",
"args": ["-y", "exposnap"]
}
}
}2. Add to your Expo app
npm install exposnap3. Configure your React Native app
import { ScreenshotWrapper } from 'exposnap';
export default function App() {
return (
<ScreenshotWrapper>
<YourApp />
</ScreenshotWrapper>
);
}The wrapper automatically discovers your MCP server and provides a draggable camera icon for manual screenshot capture.
We welcome contributions! See CONTRIBUTING.md for details.
MIT - see LICENSE for details.
This server cannot be deployed
Drive and test your React Native and Expo apps end-to-end on iOS and Android. Supports real devices, simulators, and emulators. Snapshots, taps, typing, swipes, screenshots, deep links, reloads, builds and runtime errors.
Screenshot, PDF and HTML-to-image rendering API so Claude and Cursor can see any web page.
Screenshot, PDF and HTML-to-image rendering API so Claude and Cursor can see any web page.
OCR, transcription, file extraction, and image generation for AI agents via MCP.
