About QuickChart
QuickChart MCP Server is a Model Context Protocol (MCP) server that enables AI agents (such as Claude Desktop) to generate charts using QuickChart.io. It provides two primary tools: generate_chart to create a chart URL from a Chart.js configuration, and download_chart to save the chart image locally. The server supports a wide range of chart types including bar, line, pie, doughnut, radar, polar area, scatter, bubble, radial gauge, and speedometer. Users can customize charts with labels, datasets, colors, and additional options. Installation is available via npm (@gongrzhe/quickchart-mcp-server) or through Smithery for automatic integration with Claude Desktop. This is an open-source project written in TypeScript.
Key Features
Generate chart URLs using QuickChart.io
Download chart images to local files
Supports 10+ chart types: bar, line, pie, doughnut, radar, polarArea, scatter, bubble, radialGauge, speedometer
Customizable with labels, datasets, colors, and Chart.js options
TypeScript-based MCP server for integration with Claude Desktop and other MCP clients
Installable via npm or Smithery
Pros & Cons
Pros
- Supports a wide variety of chart types
- Easy integration with MCP-compatible clients
- Free and open source
- Generates both URLs and downloadable images
- Simple Chart.js configuration format
Cons
- Relies on external QuickChart.io service
- Repository archived (no longer actively maintained as of March 2026)
- Requires internet access to generate charts
Best For
Generating chart images from AI conversations (e.g., Claude Desktop)Creating data visualizations from structured dataAutomating chart generation in MCP-compatible workflowsEmbedding chart images in documents or reports
FAQ
How do I install QuickChart MCP Server?
Install via npm: `npm install @gongrzhe/quickchart-mcp-server`, or via Smithery: `npx -y @smithery/cli install @gongrzhe/quickchart-mcp-server --client claude`.
What chart types are supported?
Supported chart types include bar, line, pie, doughnut, radar, polarArea, scatter, bubble, radialGauge, and speedometer.
How do I configure a chart?
Provide a Chart.js configuration object with 'type', 'data' (labels and datasets), and optional 'options' (e.g., title). The server converts it into a QuickChart URL.
Can I save the chart image to a file?
Yes, use the 'download_chart' tool with a chart configuration and an output file path to save the image locally.