Scanpy MCP server

@huang-sh

リポジトリ

基本情報

カテゴリ

その他

ライセンス

BSD-3-Clause

トランスポート

stdio

作者

huang-sh

Scanpy MCP server について

MCP server for Scanpy

Scanpy MCP server の設定

標準の設定はありません

このサーバーの README には解析可能な MCP 設定ブロックが含まれていません。インストール手順はリポジトリをご確認ください。

リポジトリ

Scanpy MCP server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Scanpy MCP server?

An MCP server that enables natural language interaction with the scRNA‑Seq analysis software Scanpy. It is intended for anyone wanting to perform single‑cell RNA‑Seq analysis via natural language, and for agent developers who wish to call Scanpy functions from their applications.

How to use Scanpy MCP server?

Install via pip install scanpy-mcp. To test locally, run scmcp run and configure your MCP client with "command": "scanpy-mcp" and "args": ["run"]. For remote access, use --transport shttp --port 8000 and point the client to http://localhost:8000/mcp.

Key features of Scanpy MCP server?

Read/write scRNA-Seq data using natural language
Preprocessing: filtering, QC, normalization, scaling
Highly-variable genes and PCA/Neighbors computations
Clustering and differential expression via the tool module
Plotting: violin, heatmap, dotplot

Use cases of Scanpy MCP server?

Perform complete scRNA-Seq analysis pipelines by describing steps in plain English.
Enable AI agents or chatbots to run Scanpy analyses without writing code.
Integrate Scanpy functionality into MCP‑compatible clients for interactive cell‑type annotation.
Rapidly prototype clustering or differential expression with natural language instructions.

よくある質問

What modules of Scanpy are covered?

The server supports the IO module (read/write), preprocessing (filtering, normalization, HVG, PCA, neighbors), tools (clustering, differential expression), and plotting (violin, heatmap, dotplot).

How do I run the server locally versus remotely?

Locally, invoke `scmcp run` and configure your MCP client to launch it. For remote use, start with `--transport shttp --port 8000` and set the client URL to `http://localhost:8000/mcp`.

Is this server still maintained?

No. The repository is no

「その他」の他のコンテンツ

Screenpipe

screenpipe

YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

22.0K

DeepMark

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.