You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
A comprehensive MCP (Model Context Protocol) server for ML model training, fine-tuning, and experimentation. Transform your AI assistant into a full ML engineering environment.
Features
Unified Credential Management
Encrypted vault for API keys (Lambda Labs, RunPod, Mistral, OpenAI, Together AI, etc.)
PBKDF2 key derivation with AES encryption
Never stores credentials in plaintext
Dataset Management
Register datasets from local files OR client-provided content (JSONL, CSV, Parquet)
Upload datasets directly without server filesystem access
Automatic schema inference and statistics
Train/val/test splitting
Template-based transformations
Experiment Tracking
SQLite-backed experiment storage
Version control and comparison
Fork experiments with config modifications
Full metrics history
Multi-Backend Training
Local: transformers + peft + trl for local GPU training
Mistral API: Native fine-tuning for Mistral models
Together AI: Hosted fine-tuning service
OpenAI: GPT model fine-tuning
Cloud GPU Provisioning
Lambda Labs: H100, A100 instances
RunPod: Spot and on-demand GPUs
Automatic price comparison across providers
Smart routing based on cost and availability
Remote VPS Support
Use any SSH-accessible machine (Hetzner, Hostinger, OVH, home server, university cluster)
Automatic environment setup
Dataset sync via rsync
Training runs in tmux (persistent across disconnects)
Amortized hourly cost calculation from monthly fees
Cost Estimation
Pre-training cost estimates across all providers
Real-time pricing queries
Time estimates based on model and dataset size
Ollama Integration
Deploy fine-tuned GGUF models to Ollama
Pull models from Ollama registry
Chat/inference testing directly from MCP
Model management (list, delete, copy)
Open WebUI Integration
Create model presets with system prompts
Knowledge base management (RAG)
Chat through Open WebUI (applies configs + knowledge)
Seamless Ollama ↔ Open WebUI workflow
Installation
pip install ml-lab-mcp
# With training dependencies
pip install ml-lab-mcp[training]
# With cloud provider support
pip install ml-lab-mcp[cloud]
# Everything
pip install ml-lab-mcp[training,cloud,dev]
activity - Review audit logs for patterns/anomalies
cost - Cost efficiency analysis and recommendations
dataset - Data quality and training suitability
Schedule Frequencies:
after_training - Auto-analyze when training completes
hourly / daily / weekly - Periodic reviews
Reports stored in ~/.cache/ml-lab/reports/ for historical reference.
Example Workflow
User: Fine-tune Llama 3.1 8B on my customer support data
Claude: I'll help you fine-tune Llama 3.1 8B. Let me first check your data.
[Uses dataset_register to load ./support_data.jsonl]
Found 15,000 samples. Let me estimate the costs:
[Uses train_estimate]
| Provider | Time | Cost | Availability |
|---------------|--------|--------|--------------|
| vps:hetzner-01| ~4h | $0.28* | Idle |
| Local (4090) | ~12h | $0 | Ready |
| Lambda H100 | ~2h | $5.50 | 3 available |
| Together API | ~4h | $12 | Queued |
*amortized from $200/mo
Which would you prefer?
User: Use Lambda Labs
Claude: [Uses experiment_create, then train_launch with backend=lambda]
Training started! Run ID: abc123
I'll monitor progress and let you know when it completes.
A comprehensive MCP (Model Context Protocol) server for ML model training, fine-tuning, and experimentation. Transform your AI assistant into a full ML engineering environment.