claude mcp add ightow-forge-mcp-server -- npx -y @rightnow/forge-mcp-server
{
"mcpServers": {
"ightow-forge-mcp-server": {
"command": "npx",
"args": ["-y", "@rightnow/forge-mcp-server"]
}
}
}
{
"mcpServers": {
"ightow-forge-mcp-server": {
"command": "npx",
"args": ["-y", "@rightnow/forge-mcp-server"]
}
}
}
{
"mcpServers": {
"ightow-forge-mcp-server": {
"command": "npx",
"args": ["-y", "@rightnow/forge-mcp-server"]
}
}
}
About This MCP Server
The io.github.RightNow-AI/forge-mcp-server is a developer tool that enables the creation of fast CUDA/Triton kernels from PyTorch models, allowing for significant speedups of up to 14x on real datacenter GPUs. This server connects to the Model Context Protocol, facilitating the optimization of AI models for improved performance. Developers would reach for this tool when they need to accelerate their PyTorch models for deployment on GPU-based infrastructure.
Turn PyTorch into fast CUDA/Triton kernels on real datacenter GPUs with up to 14x speedup.. This is a Model Context Protocol (MCP) server that extends AI assistants like Claude with developer tools capabilities via the stdio transport.
Package
@rightnow/forge-mcp-server on npm
HOW TO USE
Select your AI client above to get the install command. This MCP server uses the stdio transport and is available on npm.
What tools does it provide?
The forge-mcp-server server extends your AI assistant with developer tools capabilities. Once installed, your AI can use its tools automatically.
