MCP Directory

MCP ECharts

Generate Apache ECharts charts locally from AI for chart generation and data analysis.

Unverified
stdio (local)
No auth
TypeScript
View repo 242 npm

Add to your client

Copy the config for your MCP client and paste it into its config file.

Install / run
npx -y mcp-echarts

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "mcp-echarts": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-echarts"
      ]
    }
  }
}

Step-by-step guides: Add to Claude Desktop · Add to Cursor · Add to Windsurf

Before you start

  • Node.js 18 or higher
  • Optional: a MinIO or S3-compatible object storage endpoint for URL-based chart output

About MCP ECharts

MCP ECharts lets AI assistants generate Apache ECharts visualizations dynamically for chart generation and data analysis. It exposes a generic ECharts option tool plus 17 dedicated chart-type tools (bar, line, pie, area, radar, scatter, sankey, funnel, gauge, treemap, sunburst, heatmap, candlestick, boxplot, graph, parallel, tree). Output can be png, svg, or the ECharts option object, and charts are rendered entirely locally. Optional MinIO/S3 storage returns image URLs instead of Base64.

Tools & capabilities (18)

generate_echarts

Generate visual charts using Apache ECharts with an echarts option and configuration dynamically.

generate_area_chart

Generate an area chart to show data trends under continuous independent variables and observe the overall data trend.

generate_line_chart

Generate a line chart to show trends over time.

generate_bar_chart

Generate a bar chart to show data for numerical comparisons among different categories.

generate_pie_chart

Generate a pie chart to show the proportion of parts, such as market share and budget allocation.

generate_radar_chart

Generate a radar chart to display multidimensional data (four dimensions or more).

generate_scatter_chart

Generate a scatter chart to show the relationship between two variables.

generate_sankey_chart

Generate a sankey chart to visualize flow and quantities between nodes.

generate_funnel_chart

Generate a funnel chart to visualize stages of a process and conversion rates.

generate_gauge_chart

Generate a gauge chart to display a single value within a range.

generate_treemap_chart

Generate a treemap chart to display hierarchical data as nested rectangles.

generate_sunburst_chart

Generate a sunburst chart to display hierarchical data in concentric rings.

generate_heatmap_chart

Generate a heatmap chart to show the magnitude of values across two dimensions.

generate_candlestick_chart

Generate a candlestick (K-line) chart to visualize financial/stock price movements.

generate_boxplot_chart

Generate a boxplot chart to show the distribution and outliers of data.

generate_graph_chart

Generate a network graph chart from nodes and edges.

generate_parallel_chart

Generate a parallel coordinates chart to visualize high-dimensional data.

generate_tree_chart

Generate a tree chart to display hierarchical tree-structured data.

What this server can do

MCP ECharts provides tools for these capabilities — tap one to see every MCP server that does the same:

Vector & semantic search

When to use it

  • Turning tabular or structured data into charts during AI-assisted data analysis
  • Letting an AI assistant render bar, line, pie, and other charts directly in chat
  • Generating SVG/PNG chart images or ECharts option objects for embedding in apps and reports
  • Producing shareable chart image URLs via MinIO/S3 object storage

Security notes

Charts are generated fully locally without relying on any remote service. Optional MinIO/S3-compatible object storage can be configured via environment variables (e.g. MINIO_ACCESS_KEY, MINIO_SECRET_KEY) to store and serve chart images as URLs; without it, output falls back to Base64.

MCP ECharts FAQ

Does it require any remote service or API key?

No. Charts are generated fully locally and the MCP server itself needs no API key. MinIO/S3 storage is optional and configured via environment variables.

What output formats are supported?

png, svg, and the ECharts option object, with validation to help the model output correct ECharts syntax across multiple rounds.

What transports are supported?

stdio (default), plus SSE and Streamable HTTP. Run with `mcp-echarts -t sse` or `-t streamable` (default port 3033).

What happens if MinIO is not configured?

The system automatically falls back to Base64 data output, ensuring compatibility.

#echarts#charts#data-visualization#data-analysis#llm#mcp-server

Alternatives to MCP ECharts

Compare all alternatives →
Memory (Knowledge Graph)
AI, Data & Knowledge
74k

Official MCP server providing persistent, file-backed knowledge-graph memory across sessions.

Verified
stdio (local)
No auth
TypeScript
9 tools
Updated 5 months agoRepo
Sequential Thinking
AI, Data & Knowledge
62k

Structured step-by-step reasoning tool for breaking problems into revisable thought sequences.

Verified
stdio (local)
No auth
TypeScript
1 tool
Updated 6 months agoRepo
AWS Knowledge MCP
AI, Data & Knowledge
7.0k

Fully managed remote server for AWS docs, blogs, What's-New and Well-Architected guidance — no key.

Verified
HTTP (remote)
No auth
Hosted
6 tools
Updated 5 months agoRepo

Compare MCP ECharts with:

vs Memory (Knowledge Graph)vs Sequential Thinkingvs AWS Knowledge MCPvs MCP Server Chart