Install cuda4cpu in Claude Code
claude mcp add cuda4cpu -- docker run -i --rm ghcr.io/javier-cabezas/cuda4cpu:0.4.1{
"mcpServers": {
"cuda4cpu": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/javier-cabezas/cuda4cpu:0.4.1"
]
}
}
}Frequently asked questions
What does the cuda4cpu MCP server do?
Compile, run and check CUDA and HIP kernels without a GPU: wrong results, races, memory errors
Is the cuda4cpu MCP server free?
Yes, most likely. Open source and no paid account or API key is mentioned in the listing. Check the provider for current pricing.
Does cuda4cpu run locally or remotely?
Local. Runs on your machine (stdio). You install it with npx, uvx, Docker or from source.
How do I add cuda4cpu to Claude Code?
Run: claude mcp add cuda4cpu -- docker run -i --rm ghcr.io/javier-cabezas/cuda4cpu:0.4.1
More knowledge, memory & rag MCP servers
View allEpiphany
GATSV-tech/epiphany
One private, local memory your AI tools share. Cross-model, on-device, never lose a session.
Cortex Viz
cdeust/cortex-viz
Read-only visualization for Cortex memory, knowledge, sessions, traces, and codebase graphs.
iCloud
epinethrone/icloud-mcp
iCloud Mail, Calendar, Contacts, Reminders, Notes and Drive. Approval-first, self-hosted or local.
Claims
dgonzap30/claims-mcp
A claims memory for agents: assert beliefs, let them decay, surface contradictions.
Memento Protocol
myrakrusemark/memento-protocol
Persistent memory for AI agents. Store what matters, recall by meaning, skip the rest.
Cairn Remembers
CairnRemembers/cairn
Local memory your AI tools share: decisions, notes and corrections that carry across sessions.