SCMCP
About
A natural language interface for single-cell RNA sequencing (scRNA-Seq) analysis, supporting various modules from IO to enrichment.
Details
- Author
- scmcphub
- Categories
- Developer Tools
Jump to
Setup
Install SCMCP in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/scmcphub/scmcp
Follow the installation instructions in the repository README, then restart your MCP client.
An MCP server for scRNA-Seq analysis with natural language!
- IO module: Read and write scRNA-Seq data with natural language
- Preprocessing module: Filtering, quality control, normalization, scaling, highly-variable genes, PCA, Neighbors,...
- Tool module: Clustering, differential expression, etc.
- Plotting module: Violin plots, heatmaps, dotplots
- Cell-cell communication analysis
- Pseudotime analysis
- Enrichment analysis
- Anyone who wants to do scRNA-Seq analysis using natural language!
- Agent developers who want to call scanpy's functions for their applications
You can use scmcp in most AI clients, plugins, or agent frameworks that support the MCP:
- AI clients, like Cherry Studio
- Plugins, like Cline
- Agent frameworks, like Agno
scmcphub's complete documentation is available athttps://docs.scmcphub.org
A demo showing scRNA-Seq cell cluster analysis in an AI client Cherry Studio using natural language based on scmcp:
https://github.com/user-attachments/assets/93a8fcd8-aa38-4875-a147-a5eeff22a559
SCMCP provides two distinct run modes to accommodate different user needs and preferences:
In tool mode, SCMCP provides a curated set of predefined functions that the LLM can select and execute.
- Stable: Predefined functions ensure consistent and reliable execution
- Predictable: Known behavior and expected outputs
- Safe: Controlled environment with validated operations
- Limited flexibility: Restricted to available predefined functions; you need to define new tools when you need customization functions
{ "mcpServers": { "scmcp": { "command": "/home/test/bin/scmcp", "args": ["run", "--run-mode", "tool"] } } }
- https://youtu.be/VM7G-VMNhOs
- https://youtu.be/D669c0EyNzE
- https://youtu.be/b45_6fJXEIQ
In code mode, SCMCP provides a Jupyter backend that allows the LLM to generate and execute custom code. Additionally, it can generate complete Jupyter notebooks containing executable code, analysis results, and visualizations.
This mode is based on the project:https://github.com/huang-sh/abcoder
- Highly flexible: Can create custom workflows and combine operations freely
- Extensible: Supports any Python code and external libraries
- Interactive: Real-time code execution and debugging capabilities
- Less stable: Code generation may vary each time
{ "mcpServers": { "scmcp": { "command": "/home/test/bin/scmcp", "args": ["run", "--run-mode", "code"] } } }
For both modes, you can also run SCMCP remotely:
# Tool mode scmcp run --transport shttp --port 8000 --run-mode tool # Code mode scmcp run --transport shttp --port 8000 --run-mode code
{ "mcpServers": { "scmcp": { "url": "http://localhost:8000/mcp" } } }
If you have any questions, welcome to submit an issue, or contact me (hsh-me@outlook.com). Contributions to the code are also welcome!
If you use scmcp in your research, please consider citing the following works:
Wolf, F., Angerer, P. & Theis, F. SCANPY: large-scale single-cell gene expression data analysis. Genome Biol 19, 15 (2018).https://doi.org/10.1186/s13059-017-1382-0
Dimitrov D., Schäfer P.S.L, Farr E., Rodriguez Mier P., Lobentanzer S., Badia-i-Mompel P., Dugourd A., Tanevski J., Ramirez Flores R.O. and Saez-Rodriguez J. LIANA+ provides an all-in-one framework for cell–cell communication inference. Nat Cell Biol (2024).https://doi.org/10.1038/s41556-024-01469-w
Badia-i-Mompel P., Vélez Santiago J., Braunger J., Geiss C., Dimitrov D., Müller-Dott S., Taus P., Dugourd A., Holland C.H., Ramirez Flores R.O. and Saez-Rodriguez J. 2022. decoupleR: ensemble of computational methods to infer biological activities from omics data. Bioinformatics Advances.https://doi.org/10.1093/bioadv/vbac016
Weiler, P., Lange, M., Klein, M. et al. CellRank 2: unified fate mapping in multiview single-cell data. Nat Methods 21, 1196–1205 (2024).https://doi.org/10.1038/s41592-024-02303-9
This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.
Create crafted UI components inspired by the best 21st.dev design engineers.
Bring agent evaluations, observability, and synthetic test set generation directly into your IDE for free with Galileo's new MCP server
An MCP server to help AI assistants to answer questions and generate AccelByte Extend SDK code more effectively .
MCP server for AI Diagram Maker — generate beautiful software engineering diagrams directly inside Cursor, Claude Desktop, Claude Code, or any MCP-compatible AI agent
ALAPI MCP Tools,Call hundreds of API interfaces via MCP
AI-powered SVG animation generator that transforms static files into animated SVG components using the Allyson platform
MCP server that gives AI assistants on-demand access to 1,500+ amCharts docs, ~300 code examples, and 1000+ class API references.
APIMatic MCP Server is used to validate OpenAPI specifications using APIMatic. The server processes OpenAPI files and returns validation summaries by leveraging APIMatic’s API.
One shared context layer for AI agents and humans — live API specs, DB schemas, and versioned contracts across repos so every agent and teammate works from the same source of truth.
Build and deploy full-stack Next.js apps with 98 tools for React, AWS, and MongoDB
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
