- Home
- MCP servers
- ECharts
ECharts
- typescript
1
GitHub Stars
typescript
Language
5 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"zhr7777777-echarts-mcp-server": {
"command": "node",
"args": [
"your-path/echarts-mcp-server/build/index.js"
]
}
}
}You can generate a wide variety of charts with the ECharts MCP Server. This TypeScript-based server exposes chart-creation tools via the MCP protocol, letting you produce chart previews and integrate them into your apps or workflows with ease.
How to use
Connect your MCP client to the ECharts MCP Server to generate charts. You will interact with a set of chart tools (bar, line, pie, scatter, radar, heatmap, and more) that each return a chart preview URL on success. Use the provided client configuration to start the server locally or remotely, then request the specific chart type you need. The server supports both local (stdio) and remote HTTP transport modes, so you can integrate it with various hosting environments and runtimes.
How to install
Prerequisites you need on your machine before installing:
- Node.js and npm (Node.js recommended) to run the MCP server locally.
- A terminal or command prompt with network access to install dependencies.
Install dependencies and build the server locally, then start it using the recommended runtime command from the configuration.
- Install dependencies:
npm install
Build the server:
npm run build
Start the MCP server using the standard start script:
npm run start
## Configuration and running modes
The server can be run in local stdio mode or exposed via HTTP transport, depending on how you configure your MCP client. The examples below show common stdio configurations that you can copy directly into your MCP settings.
{ "mcpServers": { "echarts_server": { "command": "node", "args": [ "your-path/echarts-mcp-server/build/index.js" ] } } }
## Usage notes for transports
If you prefer a one-shot, self-contained run, you can also use a package runner that starts the server via npx. This is convenient for quick experiments or ephemeral environments.
{ "mcpServers": { "echarts_server": { "command": "npx", "args": [ "-y", "echarts-mcp-server" ] } } }
## Endpoint behavior and chart tools
The server provides a wide set of chart generation tools. Each tool focuses on a specific chart type and returns a preview URL you can open in a browser to view the chart rendered with ECharts. The available chart tool names include generate\_bar\_chart, generate\_line\_chart, generate\_pie\_chart, generate\_scatter\_chart, generate\_radar\_chart, generate\_heatmap\_chart, and generate\_general\_chart for more complex charts.
## Tools you can use
- generate\_bar\_chart: Create a bar chart. - generate\_line\_chart: Create a line chart. - generate\_pie\_chart: Create a pie chart. - generate\_scatter\_chart: Create a scatter chart. - generate\_radar\_chart: Create a radar chart. - generate\_heatmap\_chart: Create a heatmap chart. - generate\_general\_chart: Create more advanced charts such as treemap, sunburst, gauge, and others.
## Development
Install dependencies
npm install
Build the server
npm run build
Start the MCP server
npm run start
Available tools
generate_bar_chart
Generates a bar chart and returns a chart preview URL for viewing the result.
generate_line_chart
Generates a line chart and returns a chart preview URL for viewing the result.
generate_pie_chart
Generates a pie chart and returns a chart preview URL for viewing the result.
generate_scatter_chart
Generates a scatter chart and returns a chart preview URL for viewing the result.
generate_radar_chart
Generates a radar chart and returns a chart preview URL for viewing the result.
generate_heatmap_chart
Generates a heatmap chart and returns a chart preview URL for viewing the result.
generate_general_chart
Generates more advanced charts such as tree, treemap, sunburst, boxplot, candlestick, graph, sankey, funnel, gauge or themeRiver and returns a chart preview URL.