generate_bar_chart
Generate a bar chart preview link(not a chart image) which user can click to show data for numerical comparisons among different categories, such as, comparing categorical data and for horizontal comparisons.
LABSCO SUMMARY
Every tool says 'preview link, not a chart image' in its own text, which prevents the specific disappointment of expecting a picture.
A charting tool that returns a URL rather than an image is a reasonable design — ECharts is interactive, and a link preserves the hover and zoom a flattened PNG loses. What makes it work is saying so on every tool, because a model that assumes it received an image will describe one that does not exist and hand the user a broken reference. Splitting by chart type rather than taking a type parameter is the other useful choice: each tool's description says what its chart is for, which helps a model pick the right visualisation rather than defaulting to bar.
What it is
An ECharts chart generator that returns preview links rather than images: six dedicated chart types and one general tool covering the others.
What you get
- Dedicated tools for bar, line, pie, heatmap, radar and scatter, each stating what its chart type is for — scatter for the relationship between two variables, radar for multidimensional comparison, heatmap for density.
- generate_general_chart covers the types without their own tool.
- Every tool states in its own description that it returns a preview link and not a chart image, so the output is a URL to open rather than something to embed directly.
Requirements
Nothing to supply.
Setup effort
One command — npx -y echarts-mcp-server
USE CASES
01
Showing a comparison across categories
Generate the bar or pie chart and hand back the link, which stays interactive rather than flattening to an image.
02
Showing something over time
Generate a line chart for the series rather than forcing a time axis into a bar chart.
03
Showing a relationship or a density
Use scatter for the relationship between two variables, or heatmap when the question is where values concentrate.
04
Comparing several dimensions at once
Generate a radar chart, or reach for the general tool when the shape you need has no dedicated one.
7 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
generate_general_chart
Generate a chart preview link(not a chart image). Support following types: effectScatter, tree, treemap, sunburst, boxplot, candlestick, graph, sankey, funnel, gauge and themeRiver
generate_heatmap_chart
Generate a heatmap chart preview link(not a chart image) which mainly use colors to represent values, which must be used along with visualMap component.
generate_line_chart
Generate a line chart preview link(not a chart image) which users can click to show trends over time, such as, the ratio of Apple computer sales to Apple's profits changed from 2000 to 2016.
generate_pie_chart
Generate a pie chart preview link(not a chart image) which users can click to show the proportion of parts, such as, market share and budget allocation.
generate_radar_chart
Generate a radar chart preview link(not a chart image) which display multidimensional data (four dimensions or more), such as, evaluate Huawei and Apple phones in terms of five dimensions: ease of use, functionality, camera, benchmark scores, and battery life.
generate_scatter_chart
Generate a scatter chart to show the relationship between two variables, helps discover their relationship or trends, such as, the strength of correlation, data distribution patterns.
BEFORE YOU INSTALL
What to know first
Tools you get
7 tools when we connected.
Requires
npx on PATH
CONTEXT COST
Heavy Standing cost
Rated by the size of the 7 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Add the block to your client, or run the command directly.
Server setup
Configuration file
JSON
{
"mcpServers": {
"echarts-mcp-server": {
"command": "npx",
"args": [
"-y",
"echarts-mcp-server"
]
}
}
}npx
TERMINAL
npx -y echarts-mcp-server
