Chatspatial
About
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.
Explore
<details>
<summary><strong>📊 Data Formats Supported</strong></summary>
- 10x Genomics: Visium, Xenium
- Spatial Technologies: Slide-seq v2
- Multiplexed Imaging: MERFISH, seqFISH
- Standard Formats: H5AD, H5, MTX, CSV
</details>
<details>
<summary><strong>🔬 Analysis Methods (12 Categories, 75+ Methods)</strong></summary>
| Category | Methods |
|----------|---------|
| Cell Type Annotation | Tangram, scANVI, CellAssign, mLLMCellType, sc-type, SingleR |
| Spatial Domains | SpaGCN, STAGATE, Leiden clustering |
| Cell Communication | LIANA+, CellPhoneDB, CellChat (via LIANA) |
| Deconvolution | Cell2location, DestVI, RCTD, Tangram, Stereoscope, SPOTlight |
| CNV Analysis | infercnvpy, Numbat (haplotype-aware CNV analysis) |
| Spatial Variable Genes | SpatialDE, SPARK-X |
| Trajectory & Velocity | CellRank, Palantir, DPT, scVelo, VeloVI |
| Sample Integration | Harmony, BBKNN, Scanorama, scVI |
| Differential Expression | Wilcoxon, t-test, Logistic Regression (scanpy methods) |
| Gene Set Enrichment | GSEA, ORA, ssGSEA, Enrichr, Spatial EnrichMap |
| Spatial Statistics | Moran's I, Local Moran's I (LISA), Geary's C, Getis-Ord Gi*, Neighborhood Enrichment, Co-occurrence, Ripley's K/L, Bivariate Moran's I, Join Count, Network Properties, Spatial Centrality |
| Spatial Registration | PASTE, STalign |
</details>
<details>
<summary><strong>⚙️ System Requirements</strong></summary>
- Python: 3.10+ (required for MCP)
- Memory: 8GB+ RAM (16GB+ for large datasets)
- Storage: 5GB+ for dependencies
- OS: Linux, macOS, Windows (WSL recommended)
- GPU: Optional (speeds up deep learning methods)
</details>
---
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
ChatspatialCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
python --version # Should be 3.10+
pip install --upgrade pip
pip install -e ".[full]" # Recommended: All features included
<details>
<summary><strong>Option A: Claude Desktop</strong> (GUI Application)</summary>
> 💡 New to Claude Desktop? Download Claude Desktop from Anthropic's official site (available for Mac & Windows)
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
``json`
{
"mcpServers": {
"chatspatial": {
"command": "/path/to/chatspatial_env/bin/python",
"args": ["-m", "chatspatial", "server"]
}
}
}
</details>
<details>
<summary><strong>Option B: Claude Code</strong> (Terminal/IDE)</summary>
Step 1: Install Claude Code CLI
bash`
npm install -g @anthropic-ai/claude-code
Step 2: Find Your Virtual Environment Path
source chatspatial_env/bin/activate
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"chatspatial": {
"ChatSpatial": {
"command": "python",
"args": [
"--version",
"#",
"Should",
"be",
"3.10+"
]
}
}
}
}McpServers
{
"ChatSpatial": {
"command": "python",
"args": [
"--version",
"#",
"Should",
"be",
"3.10+"
]
}
}
Agentic Workflow Orchestration for Spatial Transcriptomics Analysis
</div> Eliminate the implementation tax. Focus on biological insight. ChatSpatial is an agentic workflow orchestration platform that 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 the need for manual data conversion and complex programming. 🎯 Example: Analyze spatial transcriptomics data through conversation with Claude ``text
👤 "Load my 10x Visium dataset and identify spatial domains"
🤖 ✅ Loaded 3,456 spots, 18,078 genes
✅ Identified 7 spatial domains using SpaGCN
✅ Generated spatial domain visualization
👤 "Find marker genes for domain 3 and create a heatmap"
🤖 ✅ Found 23 significant markers (adj. p < 0.05)
✅ Top markers: GFAP, S100B, AQP4 (astrocyte signature)
✅ Generated expression heatmap
`
👤 = You chatting with Claude | 🤖 = ChatSpatial MCP executing analysis
---
🚀 Why Researchers Choose ChatSpatial
<table>
<tr>
<td width="50%" valign="top">
Before: Traditional Analysis
``pythonSign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
