Chart.js MCP Server

A Model Context Protocol (MCP) server that generates beautiful charts using Chart.js v4. Perfect for data visualization in Claude Desktop, Cursor, and other MCP-compatible applications.

Just ask "Create a bubble chart showing company performance" and get professional results instantly!

🎯 What This Does

Transform your data into beautiful, professional charts instantly! This MCP server connects to your favorite AI applications and generates:

📊 Bar Charts - Perfect for comparing categories
📈 Line Charts - Great for showing trends over time
🥧 Pie & Doughnut Charts - Ideal for showing proportions
🎯 Scatter & Bubble Charts - Perfect for correlation analysis
🕸️ Radar Charts - Great for multi-dimensional comparisons
🌟 Polar Area Charts - Beautiful radial visualizations

All charts can be generated as:

📸 PNG Images (800x600px) - Perfect for saving, sharing, or embedding
🌐 Interactive HTML - Self-contained divs with hover tooltips and animations

Interactive HTML charts with hover tooltips and animations - perfect for web applications!

🖼️ See It In Action

Here's what you can create with just a simple request:

Bar Chart Perfect for comparisons	Line Chart Great for trends	Pie Chart Show proportions
Doughnut Chart Modern proportions	Radar Chart Multi-dimensional data	Scatter Chart Correlation analysis
Bubble Chart 3D relationships	Polar Area Chart Radial visualizations	And more chart types coming soon!

🚀 For Users - Quick Setup

System Requirements

Node.js 18+ - Required for running the MCP server

Using with Claude Desktop

The simplest way to use this MCP server:

Configure Claude Desktop

Add this to your Claude Desktop configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%/Claude/claude_desktop_config.json
```
{
  "mcpServers": {
    "chartjs": {
      "command": "npx",
      "args": ["@ax-crew/chartjs-mcp-server"]
    }
  }
}
```
Restart Claude Desktop

Start Creating Charts!

Try asking Claude:

"Create a bar chart showing sales data: Q1: $50k, Q2: $75k, Q3: $60k, Q4: $90k"

Using with Cursor

Add to your Cursor settings or workspace configuration:

{
  "mcpServers": {
    "chartjs": {
      "command": "npx",
      "args": ["@ax-crew/chartjs-mcp-server"]
    }
  }
}

Alternative: Install from Source

If you prefer to install from source or want to contribute:

Clone and Build

git clone https://github.com/ax-crew/chartjs-mcp-server.git
cd chartjs-mcp-server
npm install && npm run build

Configure with Local Path

{
  "mcpServers": {
    "chartjs": {
      "command": "node",
      "args": ["/full/path/to/chartjs-mcp-server/dist/index.js"]
    }
  }
}

📖 How to Use

Basic Usage

Once configured, you can ask your AI assistant to create charts using natural language:

"Create a pie chart of my budget: Housing 40%, Food 25%, Transport 15%, Entertainment 20%"
"Make a line chart showing website visitors over 6 months: Jan 1000, Feb 1200, Mar 1500, Apr 1300, May 1800, Jun 2100"
"Generate a bar chart comparing programming languages: JavaScript 65%, Python 45%, Java 35%, Go 25%"

Output Formats

You can specify the output format when creating charts:

PNG Images (Default)

"Create a bar chart as a PNG image showing sales data..."

High-quality static images (800x600px)
Perfect for documents, presentations, and sharing
Works everywhere

Interactive HTML

"Create an interactive HTML doughnut chart showing project status..."

Self-contained HTML divs with embedded Chart.js
Hover tooltips and animations
Perfect for web applications and frontends
Just inject the HTML into any webpage

Example Interactive HTML Usage:

// The AI returns HTML like this:
const chartHtml = `<div id="chart-container-123">...</div>`;

// You can inject it anywhere:
document.getElementById('dashboard').innerHTML = chartHtml;

// Works with any framework
// React: <div dangerouslySetInnerHTML={{ __html: chartHtml }} />
// Vue: <div v-html="chartHtml"></div>
// Angular: <div [innerHTML]="chartHtml"></div>

Chart Types Available

Chart Type	Best For	Example Use Case
Bar	Comparing categories	Sales by region, survey results
Line	Trends over time	Stock prices, website traffic
Pie	Parts of a whole	Budget breakdown, market share
Doughnut	Proportions with focus	Same as pie, but more modern look
Scatter	Correlation analysis	Height vs weight, sales vs advertising
Bubble	3D relationships	Revenue vs profit vs company size
Radar	Multi-factor comparison	Skill assessments, product features
Polar Area	Radial data	Seasonal data, directional analysis

Advanced Features

🎨 Custom Colors: Specify color schemes for your brand
📊 Multiple Datasets: Compare multiple data series
🏷️ Labels & Titles: Add context with custom labels
📱 Responsive: Charts work great at any size
🎛️ Chart.js Options: Full access to Chart.js v4 features
🖱️ Interactive Elements: Tooltips, hover effects, and animations (HTML format)
🔗 Framework Agnostic: HTML output works with React, Vue, Angular, and vanilla JS

🛠️ Troubleshooting

Common Issues

Chart not generating?

Check that the MCP server is properly configured in your client
Verify the server is running: ps aux | grep chartjs
Try restarting your MCP client (Claude Desktop, Cursor, etc.)

Configuration not working?

Check JSON syntax in your config file
Ensure file paths are correct
Check file permissions

Charts look wrong?

Verify your data format matches Chart.js requirements
Check for missing required fields (labels, datasets, etc.)
Try a simpler chart first to test the connection

Getting Help

Check the examples - See working chart configurations
Run tests - npm test to verify everything works
Check logs - Look for error messages in your MCP client
Open an issue - We're here to help!

🔧 For Developers - Contributing

Want to improve this MCP server? We welcome contributions!

Development Setup

# Clone and setup
git clone https://github.com/ax-crew/chartjs-mcp-server.git
cd chartjs-mcp-server
npm install

# Development workflow
npm run dev          # Watch mode for development
npm test            # Run tests
npm run build       # Build for production
npm run test:watch  # Test in watch mode

Project Structure

chartjs-mcp-server/
├── src/
│   ├── index.ts           # Main MCP server implementation
│   └── chart-schema.json  # Chart.js v4 validation schema
├── examples/              # Example configurations & outputs
│   ├── *.json            # Chart configuration examples
│   ├── *.png             # Generated chart images
│   └── README.md         # Developer examples guide
├── test/
│   └── chart-server.test.js # Comprehensive test suite
├── package.json          # Dependencies and scripts
└── tsconfig.json         # TypeScript configuration

Key Technologies

TypeScript - Type-safe development
Chart.js v4 - Chart generation engine
Node Canvas - Server-side rendering
MCP Protocol - Model Context Protocol implementation
Node.js Test Runner - Native testing (no external deps)

Testing

We have comprehensive testing to ensure reliability:

npm test                  # 24 tests across 9 suites
npm run test:integration  # CLI-based integration tests
npm run test:watch        # Development watch mode

Adding New Features

Add chart type support in src/index.ts
Create example configuration in examples/
Add tests in test/chart-server.test.js
Update documentation in both READMEs
Submit a pull request

Code Standards

✅ TypeScript with strict mode
✅ Comprehensive error handling
✅ Test coverage for all features
✅ Clear, documented code
✅ MCP protocol compliance

📋 API Reference

MCP Tool: `generateChart`

The server exposes one primary tool for chart generation:

Parameters:

chartConfig (object) - Complete Chart.js v4 configuration
outputFormat (string, optional) - Output format: 'png' (default) or 'html'
saveToFile (boolean, optional) - Save PNG to file (only applies to PNG format)

Returns:

PNG Success: { success: true, buffer: Buffer, message: string } or { success: true, pngFilePath: string, message: string }
HTML Success: { success: true, htmlSnippet: string, message: string }
Error: { success: false, error: string, message: string }

Example:

{
  "type": "bar",
  "data": {
    "labels": ["Q1", "Q2", "Q3", "Q4"],
    "datasets": [{
      "label": "Sales",
      "data": [50000, 75000, 60000, 90000],
      "backgroundColor": "rgba(54, 162, 235, 0.8)"
    }]
  },
  "options": {
    "responsive": true,
    "plugins": {
      "title": {
        "display": true,
        "text": "Quarterly Sales"
      }
    }
  }
}

📦 What's Included

✅ Complete MCP Server - Ready to use with any MCP client
✅ 8 Chart Types - All major Chart.js chart types supported
✅ Dual Output Formats - PNG images and interactive HTML divs
✅ Example Configurations - 8 working examples in /examples
✅ Visual References - Generated PNG samples for each chart type
✅ Comprehensive Tests - 24 tests ensuring reliability
✅ TypeScript Support - Full type safety and IDE support
✅ Error Handling - Graceful error handling and validation
✅ Documentation - Complete setup and usage guides

🔗 Resources

📚 Chart.js Documentation
🔌 Model Context Protocol
🎨 Example Charts - See all supported chart types
🐛 Issue Tracker
💬 Discussions

📄 License

MIT License - feel free to use this in your projects!

🌟 Star This Repo!

If this MCP server helps you create amazing charts, please give it a star ⭐ to help others discover it!

Made with ❤️ for the MCP community

freddymu/chartjs-mcp-server