ChatSpatial

MCP server for spatial transcriptomics analysis via natural language

PyPI Python 3.11+ License: MIT Docs

Before

import scanpy as sc
import squidpy as sq
adata = sc.read_h5ad("data.h5ad")
sc.pp.filter_cells(adata, min_genes=200)
sc.pp.normalize_total(adata)
sc.pp.log1p(adata)
sc.pp.highly_variable_genes(adata)
sc.tl.pca(adata)
sc.pp.neighbors(adata)
# ... 40 more lines

After

"Load my Visium data and identify
 spatial domains"

Loaded 3,456 spots, 18,078 genes
Identified 7 spatial domains
Generated visualization

Quick Start

Using Claude Code / Codex / OpenCode? Just paste this:

Install ChatSpatial following https://github.com/cafferychen777/ChatSpatial/blob/main/INSTALLATION.md

# Install uv (recommended - handles complex dependencies)
curl -LsSf https://astral.sh/uv/install.sh | sh

# Create environment and install
python3 -m venv venv && source venv/bin/activate
uv pip install chatspatial

# Configure (use your venv Python path)
claude mcp add chatspatial /path/to/venv/bin/python -- -m chatspatial server

Works with any MCP-compatible client — not just Claude. Use with OpenCode, Codex, or any client supporting Model Context Protocol. Configure your preferred LLM (Qwen, DeepSeek, Doubao, etc.) as the backend.

See Installation Guide for detailed setup including virtual environments and all MCP clients.

Use

Load /path/to/spatial_data.h5ad and show me the tissue structure

Identify spatial domains using SpaGCN

Find spatially variable genes and create a heatmap

Capabilities

Category	Methods
Spatial Domains	SpaGCN, STAGATE, GraphST, Leiden, Louvain
Deconvolution	FlashDeconv, Cell2location, RCTD, DestVI, Stereoscope, SPOTlight, Tangram, CARD
Cell Communication	LIANA+, CellPhoneDB, CellChat, FastCCC
Cell Type Annotation	Tangram, scANVI, CellAssign, mLLMCelltype, scType, SingleR
Trajectory & Velocity	CellRank, Palantir, DPT, scVelo, VeloVI
Spatial Statistics	Moran's I, Local Moran, Geary's C, Getis-Ord Gi*, Ripley's K, Neighborhood Enrichment
Enrichment	GSEA, ORA, Enrichr, ssGSEA, Spatial EnrichMap
Spatial Genes	SpatialDE, SPARK-X
Integration	Harmony, BBKNN, Scanorama, scVI
Other	CNV Analysis, Spatial Registration

60+ methods across 15 categories. Supports 10x Visium, Xenium, Slide-seq v2, MERFISH, seqFISH.

Documentation

Guide	Description
Installation	Virtual environment setup, all platforms
Quick Start	5-minute first analysis
Examples	Step-by-step workflows
Methods Reference	All 20 tools with parameters
Full Docs	Complete reference

Citation

@software{chatspatial2025,
  title={ChatSpatial: Agentic Workflow for Spatial Transcriptomics},
  author={Chen Yang and Xianyang Zhang and Jun Chen},
  year={2025},
  url={https://github.com/cafferychen777/ChatSpatial}
}

MIT License · GitHub · Issues