CubicLM is an MCP server published by CubicLM in the Science category: cubicLM is a cross-platform AI client for seamless switching between cloud APIs and local, offline inference of custom and uncensored models.
The repository has 13 stars and 0 forks, with the last commit 21 days ago. Recent commit activity is the strongest signal that reported issues will get attention.
Install
From source
git clone https://github.com/CubicLM/CubicLM
This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Ask AI
✦
Ask AI about CubicLM
Powered by Claude · Grounded in docs
I know everything about CubicLM. Ask me about installation, configuration, usage, or troubleshooting.
Security checks
6 checks have not been run yet.
Releases
v1.18.0CubicLM v1.18.0 · 26 Sep 2026Staged update-check feedback (spinner, stepper, outcome caption), GetX warning cleanup, website What's New section. Full changelog in CHANGELOG.md.
v1.15.1CubicLM v1.15.1 · 10 Sep 2026CubicLM v1.15.1 — Release Notes Fixes Release-build GGUF load crash**: R8/ProGuard keep rules for the llama plugin and its Kotlin callback — release APKs no longer die instantly (SIGABRT) when loading a model. This was the reported Honor…
No package has been published for this server, so install it from source: clone the repository and follow its README.
Is CubicLM safe to use with an AI agent?
Its trust score is 39 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.
Is CubicLM still maintained?
Yes — the latest release is v1.18.0 (26 Sep 2026), and the last commit was 21 days ago. The repository has 13 stars.