Quickchart-MCP-Server

MCP.Pizza Chef: GongRzhe

Give the assistant some labels and figures and it builds a bar, line, pie, doughnut, radar, polar area, scatter, bubble, gauge or speedometer chart. There are exactly two tools: one hands back a web link to the finished image, the other saves it as a picture file wherever you say, overwriting anything already at that name. No account or payment is needed. The project was archived by its author in 2026 and has had no code changes since May 2025.

Archived ยท archived on GitHub; no code changes since May 2025
Data
Images/Design

Use This MCP server To

Turn a short list of monthly figures into a bar chart Draw a pie chart of where my budget goes Save a line chart as an image I can email Show a single number as a speedometer-style gauge Plot two sets of numbers against each other

README

quickchart-server MCP Server

image Quickchart-MCP-Server MCP server

Smithery Badge

A Model Context Protocol server for generating charts using QuickChart.io

This is a TypeScript-based MCP server that provides chart generation capabilities. It allows you to create various types of charts through MCP tools.

Overview

This server integrates with QuickChart.io's URL-based chart generation service to create chart images using Chart.js configurations. Users can generate various types of charts by providing data and styling parameters, which the server converts into chart URLs or downloadable images.

Features

Tools

  • generate_chart - Generate a chart URL using QuickChart.io

    • Supports multiple chart types: bar, line, pie, doughnut, radar, polarArea, scatter, bubble, radialGauge, speedometer
    • Customizable with labels, datasets, colors, and additional options
    • Returns a URL to the generated chart
  • download_chart - Download a chart image to a local file

    • Takes chart configuration and output path as parameters
    • Saves the chart image to the specified location image

image

Supported Chart Types

  • Bar charts: For comparing values across categories
  • Line charts: For showing trends over time
  • Pie charts: For displaying proportional data
  • Doughnut charts: Similar to pie charts with a hollow center
  • Radar charts: For showing multivariate data
  • Polar Area charts: For displaying proportional data with fixed-angle segments
  • Scatter plots: For showing data point distributions
  • Bubble charts: For three-dimensional data visualization
  • Radial Gauge: For displaying single values within a range
  • Speedometer: For speedometer-style value display

Usage

Chart Configuration

The server uses Chart.js configuration format. Here's a basic example:

{
  "type": "bar",
  "data": {
    "labels": ["January", "February", "March"],
    "datasets": [{
      "label": "Sales",
      "data": [65, 59, 80],
      "backgroundColor": "rgb(75, 192, 192)"
    }]
  },
  "options": {
    "title": {
      "display": true,
      "text": "Monthly Sales"
    }
  }
}

URL Generation

The server converts your configuration into a QuickChart URL:

https://quickchart.io/chart?c={...encoded configuration...}

Development

Install dependencies:

npm install

Build the server:

npm run build

Installation

Installing

npm install @gongrzhe/quickchart-mcp-server

Installing via Smithery

To install QuickChart Server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @gongrzhe/quickchart-mcp-server --client claude

To use with Claude Desktop, add the server config:

On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "quickchart-server": {
      "command": "node",
      "args": ["/path/to/quickchart-server/build/index.js"]
    }
  }
}

or

{
  "mcpServers": {
    "quickchart-server": {
      "command": "npx",
      "args": [
        "-y",
        "@gongrzhe/quickchart-mcp-server"
      ]
    }
  }
}

Documentation References

๐Ÿ“œ License

This project is licensed under the MIT License.

Quickchart-MCP-Server FAQ

Is this still maintained?
No. The author archived the project, so it is now read-only on GitHub, and the last code change was in May 2025. It still runs, but nothing will be fixed. No successor is named.
Do I need an account or key?
No. It is free to use as-is, and there is nothing to sign up for.
Where does my data go?
Your labels and numbers are packed into a web link and sent to the public quickchart.io service, which draws the picture. Keep confidential figures out of it, or point the setting at your own copy of that service.
Can I use this to make a chart for a presentation?
Yes. Ask for the chart, then have it saved as an image file and drop that into your slides or an email.
Can it write over my files?
It saves wherever you tell it to, and if a file of that name is already there it is replaced without asking. Give it a fresh folder.
Which apps does it work with?
Any assistant that supports MCP servers. The setup examples cover Claude Desktop, and it can also be installed through Smithery or run in Docker.