mlx-lm

PyPI

Is mlx-lm safe to use?

The latest brin safety scan flagged mlx-lm v0.30.6 with risk indicators that warrant review. No known CVE vulnerabilities. Trust score: 75/100. Review the findings below before use. This is an automated assessment and may contain errors.

Install (safety-checked)

mlx-lm Has Warnings

Warnings detected due to potential concerns

warning
CVEs

0

Threats

0

Install Scripts

0

Risk Indicators

  • Package includes native code modules

brin Recommendations

  • This package has warnings detected. Evaluate the specific concerns before proceeding.

Install with brin add mlx-lm to automatically apply these checks before installation.

This is an automated, point-in-time assessment and may contain errors. Findings are risk indicators, not confirmed threats. Security posture may change over time. Maintainers can dispute findings via the brin review process.

mlx-lm Capabilities & Permissions

What mlx-lm can access when installed. Review these capabilities before using with AI agents like Cursor, Claude Code, or Codex.

Network Access

This package makes network requests.

arxiv.orggist.github.comgist.githubusercontent.comgithub.comhuggingface.coml-explore.github.ioplatform.openai.com
Protocols: http, https, tcp

Filesystem Access

Reads and writes to the filesystem.

.env (r).env (r).env (r)/tmp/ (rw)

Environment Variables

Accesses the following environment variables.

MLXLM_USE_MODELSCOPETOKENIZERS_PARALLELISMTRANSFORMERS_NO_ADVISORY_WARNINGS

Native Modules

Contains native code that runs outside the JavaScript sandbox.

numpy

AGENTS.md for mlx-lm

Good instructions lead to good results. brin adds mlx-lm documentation to your AGENTS.md so your agent knows how to use it properly—improving both safety and performance.

brin init

Vercel's research: 100% accuracy with AGENTS.md vs 53% without →

mlx-lm Documentation & Source Code

For the full mlx-lm README, API documentation, and source code, visit the official package registry.

Frequently asked questions about mlx-lm safety

Weekly Downloads

286.0K

Version

0.30.6

Other Versions

Last Scanned

Feb 4, 2026

Trust Score

75/100·Legitimacy signals, not safety

Capabilities

Network

Connects to: arxiv.org, gist.github.com, gist.githubusercontent.com...

Filesystem

Reads & Writes files

Environment

Accesses: MLXLM_USE_MODELSCOPE, TOKENIZERS_PARALLELISM, TRANSFORMERS_NO_ADVISORY_WARNINGS

Native

Contains native modules

Is mlx-lm Safe? | PyPI Safety Scan - brin