MCPgee
MCPgee
MCPgeeMCPgee

HoloViz MCP Server

v1.0.0•Data Science & ML•stable

✨A MCP server that provides intelligent access to the HoloViz ecosystem for humans and AIs.

aianalyticsdatadatasciencedataviz
Share:
34
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is HoloViz MCP Server?

HoloViz MCP Server is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to ✨a mcp server that provides intelligent access to the holoviz ecosystem for humans and ais.

✨A MCP server that provides intelligent access to the HoloViz ecosystem for humans and AIs.

This server falls under the Data Science & ML category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • ✨A MCP server that provides intelligent access to the HoloVi

Use Cases

Create interactive visualizations
Explore data with holoviews
Build analytics dashboards
MarcSkovMadsen

Maintainer

LicenseBSD-3-Clause
Languagepython
Versionv1.0.0
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx holoviz

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use HoloViz MCP Server

HoloViz MCP is a comprehensive Model Context Protocol server that gives AI assistants intelligent access to the entire HoloViz ecosystem — Panel, hvPlot, HoloViews, Lumen, and Datashader — so they can help developers build interactive dashboards and data visualisations without manually hunting through documentation. It provides a display server that executes Python visualisation code in an isolated environment and returns web-accessible URLs, plus component intelligence for 100+ Panel components with parameter details and usage examples. Available on PyPI as `holoviz-mcp`, it works immediately with any MCP-compatible assistant including Claude Desktop.

Prerequisites

  • Python 3.9 or higher
  • uv or pip for package installation
  • An MCP-compatible client such as Claude Desktop
  • Optional: conda if you prefer conda-forge installation
  • Basic familiarity with Panel or hvPlot for making use of AI-generated code
1

Install holoviz-mcp from PyPI

Install the package using pip or uv. The conda-forge package is also available if you prefer conda environments.

pip install holoviz-mcp
# or with conda:
conda install -c conda-forge holoviz-mcp
2

Add the server to your MCP client configuration

Edit your Claude Desktop config file to register holoviz-mcp. On macOS the file is at ~/Library/Application Support/Claude/claude_desktop_config.json.

{
  "mcpServers": {
    "holoviz": {
      "command": "uvx",
      "args": ["holoviz-mcp"]
    }
  }
}
3

Restart your MCP client

Quit and relaunch Claude Desktop (or your chosen MCP client) so it picks up the new server entry and establishes the connection.

4

Verify the tools are available

In the Claude Desktop chat window, ask the assistant to list available HoloViz tools. You should see tools for documentation search, code execution via the display server, and component discovery.

5

Optional: run with Docker

A pre-built Docker image is available for environments where you prefer containerised services.

docker run -p 8765:8765 ghcr.io/marcskovmadsen/holoviz-mcp:latest

HoloViz MCP Server Examples

Client configuration

Minimal Claude Desktop configuration using uvx to run holoviz-mcp without a global install.

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

Prompts to try

Example prompts that leverage the HoloViz MCP server's documentation access, display server, and component intelligence capabilities.

- "Create an interactive Panel dashboard with a slider that filters a DataFrame and shows an hvPlot bar chart"
- "Show me all the parameters of the Panel FileInput widget with example code"
- "Search the HoloViz docs for how to use Datashader with large datasets"
- "Generate a Panel app that displays a live-updating time-series plot and serve it so I can view it in my browser"

Troubleshooting HoloViz MCP Server

uvx command not found when starting the server

Install uv first with `pip install uv` or via the official installer at https://docs.astral.sh/uv/getting-started/installation/. Alternatively, install holoviz-mcp with pip and change the command to `holoviz-mcp` in the config.

Display server returns no URL after executing visualisation code

The display server requires network access to bind a local port. Check that no firewall rule is blocking the port, and ensure you are not running inside a sandboxed environment that restricts outbound local connections.

Panel extensions such as panel-material-ui are not detected

Install the extension into the same Python environment that runs holoviz-mcp, then restart the MCP server. The server auto-detects installed Panel extensions on startup.

Frequently Asked Questions about HoloViz MCP Server

What is HoloViz MCP Server?

HoloViz MCP Server is a Model Context Protocol (MCP) server that ✨a mcp server that provides intelligent access to the holoviz ecosystem for humans and ais. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install HoloViz MCP Server?

Follow the installation instructions on the HoloViz MCP Server GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with HoloViz MCP Server?

HoloViz MCP Server works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is HoloViz MCP Server free to use?

Yes, HoloViz MCP Server is open source and available under the BSD-3-Clause license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

HoloViz MCP Server Alternatives — Similar Data Science & ML Servers

Looking for alternatives to HoloViz MCP Server? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.

Ultrarag

★ 5.6k

A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines

RocketRide

★ 3.1k

📇 🏠 - MCP server that exposes RocketRide AI pipelines as t

Aix Db

★ 2.1k

Aix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。

NeMo Data Designer

★ 1.9k

🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.

PaperBanana

★ 1.7k

Open source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.

MiniMax

★ 1.5k

Bridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.

Browse More Data Science & ML MCP Servers

Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Data Science & MLBrowse All Servers

Quick Config Preview

{ "mcpServers": { "holoviz": { "command": "npx", "args": ["-y", "holoviz"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use HoloViz MCP Server?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides