scvi-tools MCP

An MCP (Model Context Protocol) server that gives LLMs structured access to scvi-tools — a Python library for deep probabilistic analysis of single-cell omics data.

The bundled knowledge base covers model documentation, tutorials, API reference, workflow templates, community FAQ, and the official scvi-tools Hugging Face Hub model registry.

Contents

• Installation
  • Quick install
  • MCP client configuration
  • Optional: scvi-tools runtime
  • Development install
  • Requirements
• Architecture
• Frequently asked questions
  • Why doesn’t the MCP server run my model?
  • How do I keep the knowledge base up to date?
  • Which models are covered?
  • What is the uvx command?
  • Can I use this server from R?
• References
  • Core RNA Models
  • Multimodal / CITE-seq Models
  • ATAC / Chromatin Accessibility Models
  • Velocity Models
  • Multi-sample / Batch Analysis
  • Doublet Detection
  • Cell Type Annotation
  • Spatial Transcriptomics Models
  • Methylation Models
  • Ambient RNA Removal
  • Transfer Learning
  • Background Methods