Index live · v1.3.0 · MAY 26 2026

Unsloth

Community
byCommunity

Optimize LLM fine-tuning and reduce VRAM usage.

stdioPython

Configuration

{
  "mcpServers": {
    "unsloth": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-unsloth"
      ]
    }
  }
}

Add this to your claude_desktop_config.json file.

Quick Stats

Trust LevelCommunity
Transportstdio
API KeyNot required
LanguagePython
CategoryAI & Machine Learning

Author

C

Community

Tags

fine-tuningoptimizationvramtraining

AgenticSkills Audit

Automated framework checks. Deep code review tracked separately. Read the methodology →

0/—
Not yet evaluated
Audited May 11, 2026
No source URL on file

We don't yet have a GitHub repository or hosted endpoint URL for Unsloth. Without one, the framework can't be applied. If you maintain or know this server, please submit the source URL via our submit form.

Deep framework checks (OAuth 2.1 / PKCE implementation, input validation, sandboxing) require human source review and are tracked separately. This scorecard covers programmatically verifiable signals only.