Back to code-only MCP servers

cuda4cpu

active

Run CUDA and HIP programs on CPUs, unmodified, with GCC or Clang. No GPU or CUDA toolkit needed. Debug kernels with gdb, AddressSanitizer and Valgrind, and let AI agents compile, run and check them through an MCP server.

Code-only MCP server: no hosted endpoint, so you install and run it yourself. It is not probed, graded or counted in our reachability statistics.

Get it

Repository
github.com/javier-cabezas/cuda4cpu
Package
oci: ghcr.io/javier-cabezas/cuda4cpu
Run (stdio)
docker run -i --rm ghcr.io/javier-cabezas/cuda4cpu
The usual command for this package registry; check the repository README for required settings.
License
Apache-2.0
Last update
2026-11-10
GitHub stars
★ 8

Listed in

Run this server as a hosted endpoint? Submit the endpoint and it moves to the remote directory, where it is probed and graded.