---
title: OpenProblems Spatial Transcriptomics MCP Server Demo
emoji: 🧬
colorFrom: blue
colorTo: purple
sdk: gradio
sdk_version: 5.33.0
app_file: app.py
pinned: false
license: mit
short_description: Interactive demo of Model Context Protocol server for AI-powered spatial transcriptomics workflows
---

# 🧬 OpenProblems Spatial Transcriptomics MCP Server Demo

**Interactive demonstration of a Model Context Protocol (MCP) server designed for spatial transcriptomics research.**

## 🎯 What is this?

This is a **Model Context Protocol (MCP) server** that enables AI agents like Continue.dev to automate complex bioinformatics workflows. The server provides:

- **11 specialized tools** for workflow automation (environment validation, pipeline execution, log analysis)
- **5 knowledge resources** with curated documentation (Nextflow, Viash, Docker best practices)
- **AI agent integration** for Continue.dev and other MCP-compatible tools
- **Production deployment** options via Docker and local installation

## 🚀 Features Demonstrated

### 🔧 Environment Validation
- Check bioinformatics tool installations
- Validate environment readiness for spatial workflows
- Get installation recommendations

### ⚡ Pipeline Analysis
- Validate Nextflow DSL2 syntax and structure
- Check best practices compliance
- Identify potential improvements

### 🔍 Log Analysis
- AI-powered analysis of Nextflow execution logs
- Detect common errors (OOM, process failures)
- Provide specific troubleshooting recommendations

### 📚 Knowledge Resources
- Access curated documentation for Nextflow, Viash, Docker
- Browse spatial transcriptomics pipeline templates
- Get server status and capabilities

## 🤖 AI Agent Integration

This MCP server is designed to work with AI coding assistants like **Continue.dev**. When deployed locally, AI agents can:

1. **Automatically validate** your bioinformatics environment
2. **Generate optimized** Nextflow pipelines following OpenProblems standards
3. **Debug failed** workflow executions with intelligent log analysis
4. **Access comprehensive** documentation and best practices
5. **Create production-ready** spatial transcriptomics workflows

## 🏠 Local Installation

To use the full MCP server with AI agents:

```bash
# 1. Clone and install
git clone https://github.com/openproblems-bio/SpatialAI_MCP.git
cd SpatialAI_MCP
pip install -e .

# 2. Configure Continue.dev (add to ~/.continue/config.json)
{
  "experimental": {
    "modelContextProtocolServers": [
      {
        "name": "openproblems-spatial",
        "transport": {
          "type": "stdio",
          "command": "python",
          "args": ["-m", "mcp_server.main"],
          "cwd": "/path/to/your/SpatialAI_MCP"
        }
      }
    ]
  }
}

# 3. Test the integration
# Ask your AI agent: "Check my spatial transcriptomics environment"
```

## 🧪 Try the Demo

Use the tabs above to:

1. **Environment Validation**: Check tool availability
2. **Pipeline Analysis**: Validate Nextflow syntax
3. **Log Analysis**: Debug execution issues
4. **Documentation**: Browse curated resources
5. **AI Integration**: Learn about Continue.dev setup

## 🔗 Links

- **[GitHub Repository](https://github.com/openproblems-bio/SpatialAI_MCP)**: Full source code and documentation
- **[OpenProblems Project](https://openproblems.bio)**: Community benchmarking platform
- **[Model Context Protocol](https://modelcontextprotocol.io)**: AI-tool communication standard
- **[Continue.dev](https://continue.dev)**: AI coding assistant

## 📄 License

MIT License - see the [LICENSE](https://github.com/openproblems-bio/SpatialAI_MCP/blob/main/LICENSE) file for details.

---

*Transforming spatial transcriptomics research through AI-powered workflow automation.* 🧬✨