# Scanpy

> Use this tool when you need to analyze single-cell RNA sequencing data without writing code, and want to perform tasks like clustering, dimensionality reduction, and differential expression analysis through a conversational interface. Scanpy provides a comprehensive set of tools for preprocessing, visualization, and trajectory inference, accepting AnnData objects as input and producing insights into cell type annotation and other bioinformatics workflows as output. It is particularly useful for researchers who want to leverage natural language access to complex bioinformatics analysis.

Canonical page: https://skillsregistry.net/skills/huang-sh-scanpy  
JSON: https://api.skillsregistry.net/v1/skills/huang-sh-scanpy

## Description

SCMCP is an MCP server that provides natural language access to single-cell RNA sequencing analysis through the Scanpy library. Developed by Shenghui Huang, it exposes a comprehensive set of tools organized into modules for input/output operations, preprocessing, visualization, trajectory inference, and utility functions. The server supports both stdio and server-sent events (SSE) transport protocols, making it flexible for different integration scenarios. SCMCP handles AnnData objects internally, allowing users to perform complex bioinformatics workflows like clustering, dimensionality reduction, differential expression analysis, and cell type annotation through conversational interfaces, making it particularly valuable for researchers who want to analyze single-cell data without writing code.

## Trust

- **Trust score (0–1):** 0.83
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** search
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/huang-sh-scanpy)
- **Repository:** <https://github.com/huang-sh/scmcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "huang-sh-scanpy"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/huang-sh-scanpy` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/huang-sh-scanpy/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt