Highcharts MCP Server

1

Add it to Claude Code

Run this in a terminal.

Run in terminal
claude mcp add mcp-highcharts -- npx -y mcp-highcharts@latest
README.md

Render interactive Highcharts visualizations directly within AI chat.

mcp-highcharts

Render interactive Highcharts charts inline in AI chat — VS Code, GitHub Copilot, Claude Desktop, or any MCP client with MCP Apps support.

Code_-_Insiders_15uBYM8FHt

Setup

Click a badge above, or add to your MCP config:

{
  "mcp": {
    "servers": {
      "highcharts": {
        "command": "npx",
        "args": ["-y", "mcp-highcharts@latest"]
      }
    }
  }
}
Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "highcharts": {
      "command": "npx",
      "args": ["-y", "mcp-highcharts@latest"]
    }
  }
}
HTTP mode
npx mcp-highcharts@latest --http          # http://localhost:3001/mcp
PORT=8080 npx mcp-highcharts@latest --http  # custom port

Tools

Tool Description
render_chart Any chart type — line, bar, pie, scatter, heatmap, sankey, gauge, treemap, wordcloud, and 60+ more
render_stock_chart Financial charts with navigator, range selector, and 40+ technical indicators
render_dashboard Multi-component layouts with charts, KPIs, and data grids
render_map Choropleth maps, map bubbles, map points (auto-fetches map data from CDN)
render_gantt Project timelines with tasks, dependencies, and milestones
render_grid Standalone data tables with sorting, pagination, and formatting

All tools accept the full Highcharts Options API. Title and subtitle accept string shorthand.

Prompts

Prompt What it does
chart_from_data Paste data → get the best chart
dashboard_layout Scaffold a dashboard
stock_analysis Candlestick + volume + indicators
comparison_chart Side-by-side comparison patterns
project_timeline Gantt with dependencies

Configuration

Theming

Charts auto-adapt to host light/dark mode. Override with environment variables:

{
  "env": {
    "HIGHCHARTS_THEME": "dark-unica",
    "HIGHCHARTS_OPTIONS": "./my-theme.json"
  }
}

HIGHCHARTS_OPTIONS accepts .json, .js, .mjs, .ts, or inline JSON.

Built-in themes: adaptive (default), avocado, brand-dark, brand-light, dark-blue, dark-green, dark-unica, gray, grid, grid-light, high-contrast-dark, high-contrast-light, sand-signika, skies, sunset

Schema detail

Controls how much type information is sent to the LLM:

{ "env": { "SCHEMA_DETAIL": "basic" } }
Level Description
minimal Property names only — zero context overhead
basic (default) Top-level types + descriptions + examples
full Complete recursive Highcharts type tree

Color modes

Generate monochrome palettes: "colorMode": "monochrome-blue" or any CSS color like "#7b68ee".

Data sources

Read files instead of inlining data: "dataSource": "sales.csv". Supports CSV, JSON, TSV, and HTTPS URLs. Paths are sandboxed to the workspace.

Development

npm install && npm run build && npm test

Chart types, module mappings, and schemas are auto-generated from the installed Highcharts version — just npm update highcharts and rebuild.

License

MIT

Tools (6)

render_chartRenders various chart types including line, bar, pie, scatter, heatmap, sankey, gauge, treemap, and wordcloud.
render_stock_chartRenders financial charts with navigator, range selector, and technical indicators.
render_dashboardCreates multi-component layouts with charts, KPIs, and data grids.
render_mapRenders choropleth maps, map bubbles, and map points with auto-fetched data.
render_ganttRenders project timelines with tasks, dependencies, and milestones.
render_gridRenders standalone data tables with sorting, pagination, and formatting.

Environment Variables

HIGHCHARTS_THEMESets the visual theme for charts (e.g., dark-unica, grid).
HIGHCHARTS_OPTIONSPath to a JSON, JS, or TS file containing custom chart options.
SCHEMA_DETAILControls the level of type information sent to the LLM (minimal, basic, full).

Configuration

claude_desktop_config.json
{"mcpServers": {"highcharts": {"command": "npx", "args": ["-y", "mcp-highcharts@latest"]}}}

Try it

Create a bar chart comparing the sales data from sales.csv.
Generate a stock analysis chart for the last 30 days including volume and moving average indicators.
Build a project dashboard showing the current timeline using the render_gantt tool.
Create a heatmap visualization for the provided user engagement data.

Frequently Asked Questions

What are the key features of Highcharts MCP?

Supports over 17 chart types including advanced visualizations like Sankey and Treemap.. Auto-adapts to host light/dark mode themes.. Supports external data sources including CSV, JSON, TSV, and HTTPS URLs.. Includes specialized tools for financial stock charts and project Gantt timelines.. Provides configurable schema detail levels to optimize LLM context usage..

What can I use Highcharts MCP for?

Visualizing project progress and dependencies for developers using Gantt charts.. Creating interactive financial reports and stock analysis dashboards within chat.. Quickly generating data visualizations from local CSV or JSON files for data analysis.. Building custom internal dashboards with KPIs and data grids for team reporting..

How do I install Highcharts MCP?

Install Highcharts MCP by running: npx -y mcp-highcharts@latest

What MCP clients work with Highcharts MCP?

Highcharts MCP works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Turn this server into reusable context

Keep Highcharts MCP docs, env vars, and workflow notes in Conare so your agent carries them across sessions.

Need the old visual installer? Open Conare IDE.
Open Conare