Chatspatial

Name: Chatspatial
Author: cafferychen777

@cafferychen777

About Chatspatial

Natural language-driven spatial transcriptomics analysis via MCP. Integrates 60+ analytical methods across 15 categories including preprocessing, visualization, spatial statistics, cell communication, deconvolution, and trajectory analysis.

#spatial-transcriptomics #bioinformatics #single-cell #scanpy #squidpy

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "ChatSpatial": {
      "command": "python",
      "args": [
        "--version",
        "#",
        "Should",
        "be",
        "3.10+"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Chatspatial?

Chatspatial is an agentic workflow orchestration platform for spatial transcriptomics analysis. It integrates 60+ state-of-the-art methods from fragmented Python and R ecosystems into a unified conversational interface. Built on the Model Context Protocol (MCP), it enables human-steered discovery through natural language in Claude Desktop or Claude Code, eliminating manual data conversion and complex programming.

How to use Chatspatial?

Create a Python 3.10+ virtual environment, install the package with pip install -e ".[full]", then configure Claude Desktop by adding an MCP server entry to claude_desktop_config.json or Claude Code with the claude mcp add command. Download sample data and load it using absolute paths (e.g., /Users/yourname/Downloads/card_spatial.h5ad). After setup, simply type natural language requests in Claude chat to analyze spatial transcriptomics data—no coding required.

Key features of Chatspatial

75+ analysis methods across 12 categories (cell annotation, spatial domains, deconvolution, etc.)
Supports 10x Genomics Visium, Xenium, Slide-seq v2, MERFISH, seqFISH, and standard formats (H5AD, MTX, CSV)
Natural language interface for data loading, analysis, and visualization
Publication-ready visualizations (spatial plots, heatmaps, communication networks)
Optional GPU acceleration for deep learning methods
MIT licensed for academic and commercial use

Use cases of Chatspatial

Load a 10x Visium dataset and identify spatial domains using SpaGCN
Find marker genes for a specific domain and generate expression heatmaps
Deconvolve spatial data with a reference using Cell2location or RCTD
Analyze cell–cell communication between spatial regions via LIANA+ and CellPhoneDB
Detect spatially variable genes