io.github.RightNow-AI/forge-mcp-server

Official

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

Convert PyTorch models to optimized CUDA/Triton kernels for GPU datacenters.

Install

claude_desktop_config.json

{
  "mcpServers": {
    "forge-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@rightnow/forge-mcp-server@1.0.2"
      ]
    }
  }
}