The leclap Model Context Protocol (MCP) server provides seamless integration between AI assistants (such as Claude Desktop, Cursor, and Claude Code) and Deterministic video composition from one JSON template — renders on Node, in the browser via WebAssembly, and fully on-device on React Native. No server, no upload, no generative model. Agent-callable over MCP. By connecting this server, your AI agent gains specialized capabilities to inspect, query, and automate tasks within the Browser/Web domain.
Once installed in Claude Desktop or Cursor, try asking your assistant:
Copy the config for your editor. Verify environment variables or setup notes in the README.
Add to claude_desktop_config.json:
{
"mcpServers": {
"leclap": {
"command": "npx",
"args": [
"-y",
"heristop/leclap"
]
}
}
}
<div align="center"> <img src="apps/leclap-web/public/pwa-512x512.png" alt="LeClap" width="104" height="104" /> Deterministic, on-device, agent-callable video — composed by prompt or by hand. Describe a video in one JSON _template_ — sections, filters, music, overlays — then render that same template on a phone (React Native, on-device) or in the browser (WebAssembly). No upload, no server, no generative model: the render is deterministic and reproducible, not sampled.