✨ HoloViz MCP

A comprehensive Model Context Protocol (MCP) server that provides intelligent access to the HoloViz ecosystem, enabling AI assistants to help you build interactive dashboards and data visualizations with Panel, hvPlot, Lumen, Datashader and your favorite Python libraries.

📖 Full Documentation | 🚀 Quick Start | 🐳 Docker Guide

✨ What This Provides

Documentation Access: Search through comprehensive HoloViz documentation, including tutorials, reference guides, how-to guides, and API references.

Component Intelligence: Discover and understand 100+ Panel components with detailed parameter information, usage examples, and best practices. Similar features are available for hvPlot.

Extension Support: Automatic detection and information about Panel extensions such as Material UI, Graphic Walker, and other community packages.

Smart Context: Get contextual code assistance that understands your development environment and available packages.

🎯 Why Use This?

• ⚡ Faster Development: No more hunting through docs - get instant, accurate component information.
• 🎨 Better Design: AI suggests appropriate components and layout patterns for your use case.
• 🧠 Smart Context: The assistant understands your environment and available Panel extensions.
• 📖 Always Updated: Documentation stays current with the latest HoloViz ecosystem changes.
• 🔧 Zero Setup: Works immediately with any MCP-compatible AI assistant.

🚀 Quick Start

Requirements

• Python 3.11+ and uv
• VS Code with GitHub Copilot, Claude Desktop, Cursor, or any other MCP-compatible client

Installation

Install HoloViz MCP as a uv tool:

uv tool install holoviz-mcp[panel-extensions]

Create the documentation index (takes up to 10 minutes on first run):

uvx --from holoviz-mcp holoviz-mcp-update

Configure Your IDE

VS Code + GitHub Copilot: Add this configuration to your mcp.json:

{
  "servers": {
    "holoviz": {
      "type": "stdio",
      "command": "uvx",
      "args": ["holoviz-mcp"]
    }
  },
  "inputs": []
}

Claude Desktop: Add to your configuration file (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

{
  "mcpServers": {
    "holoviz": {
      "command": "uvx",
      "args": ["holoviz-mcp"]
    }
  }
}

Cursor: Go to Cursor Settings → Features → Model Context Protocol → Add Server:

{
  "name": "holoviz",
  "command": "uvx",
  "args": ["holoviz-mcp"]
}

Restart your IDE and start asking about Panel components!

Using Docker

For containerized deployment:

# Pull the latest image
docker pull ghcr.io/marcskovmadsen/holoviz-mcp:latest

# Run with HTTP transport
docker run -it --rm \
  -p 8000:8000 \
  -e HOLOVIZ_MCP_TRANSPORT=http \
  -v ~/.holoviz-mcp:/root/.holoviz-mcp \
  ghcr.io/marcskovmadsen/holoviz-mcp:latest

See the Docker Guide for more details.

💡 Example Usage

Ask your AI assistant questions like:

• "What Panel components are available for user input?"
• "Show me how to create a dashboard with Panel Material UI components"
• "What parameters does the Button component accept?"
• "How do I deploy a Panel application?"

Watch the HoloViz MCP Introduction on YouTube to see it in action.

📚 Learn More

Check out the holoviz-mcp documentation:

• Tutorials: Step-by-step guides to get you started
• How-To Guides: Practical guides for common tasks
• Explanation: Understanding concepts and architecture
• Reference: API documentation and technical details

❤️ Contributing

We welcome contributions! See our Contributing Guide for details.

📄 License

HoloViz MCP is licensed under the BSD 3-Clause License.

🔗 Links

• GitHub: MarcSkovMadsen/holoviz-mcp
• Documentation: marcskovmadsen.github.io/holoviz-mcp
• PyPI: pypi.org/project/holoviz-mcp
• Docker: ghcr.io/marcskovmadsen/holoviz-mcp
• HoloViz Community: Discord | Discourse

---

Note: This MCP server can execute arbitrary Python code when serving Panel applications (configurable, enabled by default). See Security Considerations for details.