HoloViz MCP

What is HoloViz MCP about?

HoloViz MCP offers a comprehensive Model Context Protocol server that connects large language models and users to the full suite of HoloViz libraries (Panel, hvPlot, Lumen, Datashader, etc.). It indexes documentation, component metadata, and examples, allowing instant code suggestions, component discovery, and on‑demand rendering of visualizations.

How to use HoloViz MCP?

1. Installation – install the package via pip or conda (e.g., pip install holoviz-mcp).
2. Start the server – run the provided CLI entry point (e.g., python -m holoviz_mcp).
3. Integrate with an AI assistant – configure the assistant to call the MCP endpoint for code completion, component lookup, or to execute a holoviz_display request.
4. Render visualizations – send Python code that creates a Panel app; the server returns a shareable URL where the visualization is hosted.

Key Features of HoloViz MCP

• Documentation Search – full‑text search across tutorials, how‑to guides, and API references.
• Display Server – isolated execution of Panel code with instant, web‑accessible URLs.
• Agent Skills – ready‑to‑use skills for LLMs to request component info, generate plots, or launch dashboards.
• Component Intelligence – over 100 Panel components and hvPlot functions with parameter details and usage examples.
• Extension Detection – automatic discovery of installed Panel extensions (Material UI, Graphic Walker, etc.).
• Smart Context – code assistance that respects the current Python environment and available libraries.
• Zero‑Setup Mode – works out‑of‑the‑box with any MCP‑compatible AI assistant.

Use Cases of HoloViz MCP

• Rapid Prototyping – developers ask an LLM for a specific plot type; MCP returns ready‑to‑run code and a live preview.
• Interactive Documentation – embed a searchable UI in docs that shows component examples on demand.
• AI‑Powered Dashboard Builder – an assistant suggests layout components, fills in callbacks, and instantly renders the dashboard.
• Teaching & Workshops – participants can experiment with visualizations without installing the full HoloViz stack; the server handles execution.
• Secure Evaluation – sandboxed execution of user‑provided code for internal data‑exploration tools.

FAQ from the HoloViz MCP

Q: Which languages can call the server? A: The server exposes a REST‑like MCP interface, usable from any language that can make HTTP requests (Python, JavaScript, etc.).

Q: Do I need Docker? A: Docker is optional; it provides an isolated environment. You can also run the server directly after installing the Python package.

Q: How is code execution secured? A: Execution runs in an isolated subprocess with configurable resource limits. See the Security Considerations guide for sandbox options.

Q: Can I add my own custom HoloViz extensions? A: Yes. Once installed in the same environment, the server auto‑detects them and includes their metadata in searches.

Q: How does the server integrate with LLMs? A: LLMs can invoke the MCP endpoint as a tool/skill, requesting component details, generating code snippets, or asking the server to render a plot and return the URL.

✨ 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 | 🤗 Explore the Tools

✨ What This Provides

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

Display Server: Create and share Python visualizations with instant URLs. The holoviz_display tool executes code in an isolated server and provides web-accessible visualizations that you can view, share, and manage.

Agents Skills: Agents and Skills for LLMs.

Component Intelligence: Discover and understand 100+ Panel components with detailed parameter information and usage examples. 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.

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.