MCP 服务器

makechartswithai

MCP server that enables AI agents to recommend and generate charts from datasets using natural language, supporting 46 chart types and multiple output formats.

README

Make Charts With AI — MCP Server

The Make Charts With AI MCP server exposes AI-powered chart recommendation and generation capabilities as standard Model Context Protocol (MCP) tools for AI agents — Claude Desktop, Cursor, Antigravity, VS Code, and more.

npm package: makechartswithai

⚡ Quick Start

1. Get an API Key

Visit makechartswithai.online/mcp and generate a free anonymous API key (5 tool calls per key).

2. Add to Your MCP Client

Add the following to your MCP client configuration file (claude_desktop_config.json, mcp_config.json, etc.):

{
  "mcpServers": {
    "makechartswithai": {
      "command": "npx",
      "args": ["-y", "makechartswithai"],
      "env": {
        "MAKECHARTSWITHAI_API_KEY": "mcwai_ak_your_key_here",
        "MAKECHARTSWITHAI_BACKEND_URL": "https://makechartswithai.online"
      }
    }
  }
}

That's it — your AI agent can now recommend and generate charts.

🛠️ Available MCP Tools

1. `recommend_charts`

Analyzes raw datasets (JSON, CSV, Markdown tables, or natural language prompts) and suggests optimal chart types with confidence scores and rationale.

Inputs:

dataset_json (string, optional): Raw JSON data array or object string.
dataset_content (string, optional): CSV, Markdown table, or plain text data.
user_intent (string, optional): Natural language explanation of what you want to visualize.
focus_columns (string[], optional): Target column names to prioritize.

2. `generate_chart`

Generates a production-ready chart specification and returns the output in your choice of format (share_link, svg, png). Rendering engine (vegalite, echarts, chartjs) is automatically determined based on chart type capabilities.

Inputs:

dataset_json (string, optional): Raw JSON data string.
dataset_content (string, optional): Tabular dataset (CSV, Markdown).
user_intent (string, optional): Natural language visualization prompt.
preferred_chart_type (string enum, optional): One of 46 supported chart types (Bar Chart, Grouped Bar Chart, Stacked Bar Chart, Line Chart, Scatter Plot, Pie Chart, Area Chart, Heatmap, Radar Chart, Sunburst Chart, Sankey Diagram, etc.).
output_format (enum, optional: "share_link" | "svg" | "png", default: "share_link"):
- "share_link": Returns public view and edit URLs on makechartswithai.online.
- "svg": Renders and returns vector SVG XML markup string.
- "png": Renders and returns high-res PNG image payload (image/png base64 + saved file artifact).

🔑 Environment Variables

Variable	Required	Description
`MAKECHARTSWITHAI_API_KEY`	✅	Your API key from makechartswithai.online/mcp
`MAKECHARTSWITHAI_BACKEND_URL`	No	Backend URL (defaults to `https://makechartswithai.online`)

Legacy aliases: CHARTIT_API_KEY and CHARTIT_BACKEND_URL are also supported for backward compatibility.

📊 Supported Chart Types (46)

Area Chart, Bar Chart, Bar Table, Boxplot, Bubble Chart, Bullet Chart, Bump Chart, Calendar Heatmap, Candlestick Chart, Choropleth, Combo Chart, Connected Scatter Plot, Density Plot, Doughnut Chart, ECDF Plot, Funnel Chart, Gantt Chart, Gauge Chart, Grouped Bar Chart, Heatmap, Histogram, KPI Card, Line Chart, Lollipop Chart, Map, Network Graph, Parallel Coordinates, Pie Chart, Pyramid Chart, Radar Chart, Range Area Chart, Ranged Dot Plot, Regression, Rose Chart, Sankey Diagram, Scatter Plot, Slope Chart, Sparkline, Stacked Bar Chart, Streamgraph, Strip Plot, Sunburst Chart, Tree, Treemap, Violin Plot, Waterfall Chart.