Last updated
March 16, 2026
MCP profile
Github RightNow AI Forge Mcp Server
Turn PyTorch into fast CUDA/Triton kernels on real datacenter GPUs with up to 14x speedup.
Developer ToolsPackageJavaScript/TypeScriptOpen SourceExternal
Visibility
Public
ByRegistry
About This MCP Server
Forge MCP Server
Swarm agents that turn slow PyTorch into fast CUDA/Triton kernels, from any AI coding agent.
Forge transforms PyTorch models into production-grade CUDA/Triton kernels through automated multi-agent optimization. Using 32 parallel AI agents with inference-time scaling, it achieves up to 14x faster inference than torch.compile(mode='max-autotune-no-cudagraphs') while maintaining 100% numerical correctness.
This MCP server connects any MCP-compatible AI coding agent to Forge. Your agent submits PyTorch code, Forge optimizes it with swarm agents on real datacenter GPUs, and returns the fastest kernel as a drop-in replacement.
1. Authenticate: The agent calls forge_auth, which opens your browser. Sign in once, tokens are stored locally at ~/.forge/tokens.json and auto-refresh. 2. Optimize: The agent sends your PyTorch code via forge_optimize. The MCP server POSTs to the Forge API and streams SSE events in real time. 3. Benchmark: 32 parallel Coder+Judge agents generate kernels, compile them, test correctness against the PyTorch reference, and profile performance on real datacenter GPUs. 4. Return: The MCP server collects all results and returns the optimized code, speedup metrics, and iteration history. The output is a drop-in replacement for your original code.
Each optimization costs 1 credit. Credits are only charged for successful runs (speedup >= 1.1x). Failed runs and cancelled jobs are not charged.
Capabilities
Optimize existing kernels - Submit PyTorch code, get back an optimized Triton/CUDA kernel benchmarked against torch.compile(max-autotune)Generate new kernels - Describe an operation (e.g. "fused LayerNorm + GELU + Dropout"), get a production-ready optimized kernel32 parallel swarm agents - Coder+Judge agent pairs compete to discover optimal kernels, exploring tensor core utilization, memory coalescing, shared memory tiling, and kernel fusion simultaneouslyReal datacenter GPU benchmarking - Every kernel is compiled, tested for correctness, and profiled on actual datacenter hardware250k tokens/sec inference - Results in minutes, not hoursSmart detection - The agent automatically recognizes when your code would benefit from GPU optimizationOne-click auth - Browser-based OAuth sign-in. No API keys to manage.
Specifications
Status
live
Industry
Developer Tools
Category
General
Server type
Package
Language
JavaScript/TypeScript
License
Open Source
Verified
Yes
Hosting
Hosting Options
- Package
API
Integrate this server into your application. Choose a connection method below.
1
Configure
Configuration
json
{
"mcpServers": {
"forge": {
"command": "npx",
"args": ["-y", "@rightnow/forge-mcp-server"]
}
}
}Performance
Usage
Quick Reference
- Name
- Github RightNow AI Forge Mcp Server
- Function
- Turn PyTorch into fast CUDA/Triton kernels on real datacenter GPUs with up to 14x speedup.
- Transport
- Package
- Language
- JavaScript/TypeScript
- Source
- External (Registry)
- License
- Open Source
Get started
Ready to integrate this MCP server?
Book a demo to see how this server fits your workflow, or explore the full catalog.