Turn PyTorch into fast CUDA/Triton kernels on real datacenter GPUs with up to 14x speedup.

{
  "mcpServers": {
    "iogithubrightnow-aiforge": {
      "command": "npx",
      "args": [
        "-y",
        "@rightnow/forge-mcp-server"
      ]
    }
  }
}