data-visualization

Q: How to install data-visualization?

Open your MCP config: ~/.claude.json. Then add the config to "mcpServers": { "data-visualization": { "command": "...", "args": [] } }. Finally, /mcp in Claude Code.

Q: What is data-visualization best for?

data-visualization is categorized under Data & Analytics. It covers: design, python, data-&-analytics.

New

6.6kSmitheryData & Analyticsby anthropics

Create effective data visualizations with Python (matplotlib, seaborn, plotly). Use when building charts, choosing the right chart type for a dataset, creating publication-quality figures, or applying design principles like accessibility and color theory.

First seen 5/22/2026

Summary

This skill enables you to create effective data visualizations using Python libraries like matplotlib, seaborn, and plotly.

It helps you choose the right chart type for your dataset, design publication-quality figures, and apply principles such as accessibility and color theory.
Ideal for developers who need to communicate insights visually in reports, dashboards, or presentations.

Install & Usage

Open your MCP config

~/.claude.json

Add the server config

Add the configuration to "mcpServers": { "data-visualization": { "command": "...", "args": [] } }

Restart Claude Code

/mcp

Use Cases

Generate a line chart showing monthly sales trends over the past year from a CSV file.

Create a bar chart comparing average response times across different service tiers.

Design a heatmap to visualize correlation matrix of features in a dataset.

Build an interactive scatter plot with tooltips for exploring customer segmentation data.

Produce a publication-ready figure with custom color palette, labels, and annotations for a research paper.

Apply colorblind-friendly color schemes and accessible design to an existing visualization.

Usage Examples

/data-visualization Create a line chart from sales_data.csv showing monthly revenue trends with a title and grid.

Use matplotlib to plot a histogram of age distribution from the dataset, with 20 bins and a kernel density estimate overlay.

Generate a grouped bar chart comparing quarterly profits by region using seaborn, with a colorblind-friendly palette.

View source on GitHub

designpythondata-&-analytics

Security Audits

LicenseUnknownSourceWarnRepositoryPass

Frequently Asked Questions

What is data-visualization?

This skill enables you to create effective data visualizations using Python libraries like matplotlib, seaborn, and plotly. It helps you choose the right chart type for your dataset, design publication-quality figures, and apply principles such as accessibility and color theory. Ideal for developers who need to communicate insights visually in reports, dashboards, or presentations.

How to install data-visualization?

To install data-visualization: open your mcp config (~/.claude.json), then add the config to "mcpServers": { "data-visualization": { "command": "...", "args": [] } }. Finally, /mcp in Claude Code.

What is data-visualization best for?

data-visualization is a mcp categorized under Data & Analytics. It is designed for: design, python, data-&-analytics. Created by anthropics.

What can I use data-visualization for?

data-visualization is useful for: Generate a line chart showing monthly sales trends over the past year from a CSV file.; Create a bar chart comparing average response times across different service tiers.; Design a heatmap to visualize correlation matrix of features in a dataset.; Build an interactive scatter plot with tooltips for exploring customer segmentation data.; Produce a publication-ready figure with custom color palette, labels, and annotations for a research paper.; Apply colorblind-friendly color schemes and accessible design to an existing visualization..