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., "@@xbuildy/wave-compute-mcp List my Base44 backend functions"
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.
The only MCP that gives Cursor developers access to Base44 backend management + decentralized GPU compute via Theta EdgeCloud.
Add to ~/.cursor/mcp.json:
{
"mcpServers": {
"wave-compute": {
"command": "npx",
"args": ["-y", "@xbuildy/wave-compute-mcp"]
}
}
}{
"mcpServers": {
"wave-compute": {
"url": "https://dependable-energy-production.up.railway.app/sse"
}
}
}Related MCP server: @willpowell8/cursor-cloud-agent-mcp
6 b44_* — Base44 entity CRUD, function deploy/logs (no Wave OS account needed)
8 theta_* — Theta GPU compute, AI chat, image/video generation (requires Wave OS account)
14 wave_* — Wave OS Assistant remote control (Eddie's personal setup)
npm login
npm publish --access publicCursor → npx @xbuildy/wave-compute-mcp (stdio)
↓
oswave.io/api/functions/mcpRouter (Base44 backend)
↓
┌──────────┼──────────┐
b44_* theta_* wave_*
(Base44) (Theta GPU) (Wave Assistant)MIT License. Built by xBuildy.
This server cannot be deployed
Real-time chat for AI agents. Claude Code, Cursor, Cline and Codex join channels over MCP.
One PAT, any MCP agent: Vercel, GitHub, Cloudflare, Supabase, GCP — unified dev infra gateway.
Hosted MCP server for AI-driven data ops. Create apps, manage schemas, and CRUD structured data.
Connect MCP clients to 2,000+ AI models without managing provider API keys.
