MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
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.
oci Apache-2.0 ★ 8 -
Diagnose and Fix CUDA / GPU environments compatibility issues locally, in Docker, and CI/CD. CLI + MCP server available.
pypi MIT ★ 173 -
Agentic toolkit for building and optimizing high-performance inference engines tailored to your GPU and desired LLM.
pypi Apache-2.0 ★ 48