unsloth-mcp-server: Instructions file for Claude Code

CLAUDE.md

unsloth-mcp-server CLAUDE.md is an instructions file for Claude Code from ScientiaCapital/unsloth-mcp-server. It costs 378 tokens per session, scanned A, original, Apache-2.0.

Project instructions for an MCP server that gives Claude access to Unsloth model fine-tuning, GPU management, knowledge capture, and cost tracking.

In plain words
What is it for?
Use them when changing model training, RunPod jobs, OCR or training-data workflows, checkpoints, cost tracking, or related tests.
Why use it?
They state the supported AI providers, where keys belong, current project status, and the main tool areas.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is ScientiaCapital/unsloth-mcp-server's own configuration. It tells Claude Code how to work on unsloth-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything unsloth-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ScientiaCapital/unsloth-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ScientiaCapital/unsloth-mcp-server/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ScientiaCapital/unsloth-mcp-server

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for unsloth-mcp-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/scientiacapital/unsloth-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/scientiacapital/unsloth-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/scientiacapital/unsloth-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/scientiacapital/unsloth-mcp-server/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for unsloth-mcp-server CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/scientiacapital/unsloth-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/scientiacapital/unsloth-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 378 This file is loaded in full into every session.
When invoked 378 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00378 $0.00378
Opus 5 $0.00189 $0.00189
Sonnet 5 $0.00076 $0.00076
Haiku 4.5 $0.00038 $0.00038

Measured 9d ago against content hash 495b663323fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

unsloth-mcp-server CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 58 lines

What it actually says

Unsloth MCP Server

Updated: 2026-01-18 Status: 33 tools working, 180 tests passing, training has environment issues

Critical Rules

  • NO OpenAI - Use Anthropic Claude or Google Gemini only
  • API keys in .env only - Never hardcode
  • RunPod API key stored in .env

What This Project Is

MCP server giving Claude access to Unsloth fine-tuning. 33 tools for model training, RunPod GPU management, knowledge capture, and cost tracking.

Current Status

Component Status
MCP tools (33) Working
Test suite (180) Passing
RunPod pod management Working
Knowledge capture Working
GRPO training Dtype issues
SFT training Environment-dependent

Key Files

src/index.ts          # Main MCP server (33 tools)
src/utils/runpod.ts   # RunPod API client
src/utils/checkpoint.ts # Training checkpoints
src/utils/cost-tracker.ts # GPU cost tracking
src/knowledge/        # OCR + training data pipeline
src/__tests__/        # 180 tests

Tool Categories

  • Core (12): finetune_model, load_model, export_model, etc.
  • Knowledge (10): OCR, enhancement, training pair generation
  • RunPod (11): Pod lifecycle, training jobs, cost estimation

Development

npm run build    # Build TypeScript
npm run test     # 180 tests
npm run start    # Start server

Environment

RUNPOD_API_KEY=rpa_XXX
HUGGINGFACE_TOKEN=hf_XXX  # Optional
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 58 lines · 378 tokens per session scan A 495b663323fd

Subscribe to this mod's changes

unsloth-mcp-server CLAUDE.md is an instructions file published in the GitHub repository ScientiaCapital/unsloth-mcp-server (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 378 tokens to every session, about $0.0019 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens