vchart-mcp-server
OfficialThe vchart-mcp-server enables AI assistants to generate interactive charts and visualizations through the Model Context Protocol (MCP) using the VChart library.
Chart Types:
Cartesian Charts: line, area, bar, waterfall, funnel, and animated ranking bar charts
Polar Charts: radar, rose, and pie charts
Hierarchical Charts: sunburst, treemap, and circle packing charts
Progress Charts: linear, circular, gauge, and liquid charts for normalized values (0-1)
Specialized Charts: word clouds, Venn diagrams, range column charts, dual-axis charts, scatter/bubble charts, Sankey diagrams, and heatmaps
Output Formats:
Image (PNG/JPG) for embedding in documents
Interactive HTML for web display
VChart spec objects for programmatic use
Customization Features:
Chart dimensions (width/height), titles, and subtitles
Theme selection (light/dark) and custom color palettes
Background colors and detailed axis configuration (labels, grids, ticks, titles, orientation)
Stacking and percentage modes for relevant chart types
Deployment & Integration:
Multiple transport options (stdio for desktop apps, SSE/streamable for web)
Works with Claude, Cursor, VSCode, and other MCP-compatible applications
Private deployment support via custom image generation servers
Natural language chart creation through AI assistant integration
Allows running the VChart MCP server as a standalone Node.js application with SSE or Streamable transport, enabling integration with web-based AI applications beyond desktop clients.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@vchart-mcp-server generate a bar chart showing monthly sales data for 2024"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol (MCP) server for the @visactor/vchart that enables AI assistants to generate interactive charts and visualizations.
English | 简体中文
Table of Contents
Related MCP server: MCP Server Chart
Features
Chart Output Formats
Each chart can be generated in multiple formats:
Image - PNG/JPG image format for embedding (default)
Spec - VChart spec object for programmatic use
HTML - Interactive HTML chart for web display
Common Parameters Supported by All Charts
Parameter | Description | Type/Options | Default |
| Output format |
|
|
| Chart width | Number |
|
| Chart height | Number |
|
| Chart title | String | Optional |
| Chart subtitle | String | Optional |
| Title position | String | Optional |
| Chart theme | String | Optional |
| Background color | String | Optional |
| Color palette | Array/String | Optional |
Supported Chart Types and Tools
generate_cartesian_chart
Generates Cartesian coordinate system charts, including area, bar, line, waterfall, funnel, and animated ranking bar charts.
Parameter | Description | Type | Required |
| Data object array | Array | Yes |
| Chart type |
| Yes |
| X axis field name |
| Yes |
| Y axis field name |
| Yes |
| Color mapping field |
| Optional |
| Time field for animated ranking bar chart |
| Optional |
| Stack or percent mode |
| Optional |
| Display bar chart horizontally (as bar chart) |
| Optional |
| X axis type |
| Optional |
| X axis position |
| Optional |
| X axis title |
| Optional |
| Show X axis grid lines |
| Optional |
| Show X axis labels |
| Optional |
| Show X axis ticks |
| Optional |
| Y axis type |
| Optional |
| Y axis position |
| Optional |
| Y axis title |
| Optional |
| Show Y axis grid lines |
| Optional |
| Show Y axis labels |
| Optional |
| Show Y axis ticks |
| Optional |
generate_polar_chart
Generates polar coordinate system charts, including radar, rose, and pie charts.
Parameter | Description | Type/Options | Required |
| Data object array | Array | Yes |
| Chart type |
| Yes |
| Category field name |
| Yes |
| Value field name |
| Yes |
| Color mapping field |
| Optional |
| Angle axis title |
| Optional |
| Show angle axis grid lines |
| Optional |
| Show angle axis labels |
| Optional |
| Show angle axis ticks |
| Optional |
| Angle axis type |
| Optional |
| Radius axis title |
| Optional |
| Show radius axis grid lines |
| Optional |
| Show radius axis labels |
| Optional |
| Show radius axis ticks |
| Optional |
| Radius axis type |
| Optional |
generate_hierarchical_chart
Generates hierarchical charts, including treemap, circle packing, and sunburst charts.
Parameter | Description | Type/Options | Required |
| Data object array | Array | Yes |
| Chart type |
| Yes |
| Color mapping field |
| Yes |
| Value mapping field |
| Yes |
generate_progress_chart
Generates progress charts, including circular, linear, gauge, and liquid charts.
Parameter | Description | Type/Options | Required |
| Data object array | Array | Yes |
| Chart type |
| Yes |
| Progress value field name |
| Yes |
| Color mapping field (optional for liquid, required otherwise) |
| Optional |
generate_wordcloud_venn
Generates word cloud or Venn diagrams, suitable for displaying keywords and frequencies in text data.
Parameters:
Parameter | Description | Type/Options | Required |
| Data object array | Array | Yes |
| Chart type |
| Yes |
| Text field or Venn set field name |
| Yes |
| Value field name (required for Venn) |
| Optional |
generate_range_column_chart
Generates horizontal range bar charts, suitable for displaying data ranges and comparisons.
Parameter | Description | Type/Options | Required |
| Data object array |
| Yes |
| Category field name |
| Yes |
| Value field names |
| Yes |
| Color mapping field |
| Optional |
| X axis type |
| Optional |
| X axis position |
| Optional |
| X axis title |
| Optional |
| Show X axis grid lines |
| Optional |
| Show X axis labels |
| Optional |
| Show X axis ticks |
| Optional |
| Y axis type |
| Optional |
| Y axis position |
| Optional |
| Y axis title |
| Optional |
| Show Y axis grid lines |
| Optional |
| Show Y axis labels |
| Optional |
| Show Y axis ticks |
| Optional |
generate_dual_axis_chart
Combination chart with two Y axes, for comparing two metrics with different units.
Parameter | Description | Type/Options | Required |
| Data object array |
| Yes |
| X axis field name |
| Yes |
| Two Y axis field names |
| Yes |
| Color mapping field |
| Optional |
| Stack or percent mode |
| Optional |
| X axis position |
| Optional |
| X axis title |
| Optional |
| Show X axis grid lines |
| Optional |
| Show X axis labels |
| Optional |
| Show X axis ticks |
| Optional |
| Left Y axis title |
| Optional |
| Left Y axis grid lines |
| Optional |
| Left Y axis labels |
| Optional |
| Left Y axis ticks |
| Optional |
| Right Y axis title |
| Optional |
| Right Y axis grid lines |
| Optional |
| Right Y axis labels |
| Optional |
| Right Y axis ticks |
| Optional |
generate_scatter_chart
Displays the relationship between two variables, suitable for discovering patterns and outliers.
Parameter | Description | Type/Options | Required |
| Data object array |
| Yes |
| X axis field name |
| Yes |
| Y axis field name |
| Yes |
| Color mapping field |
| Optional |
| Size mapping field |
| Optional |
| X axis type |
| Optional |
| X axis position |
| Optional |
| X axis title |
| Optional |
| Show X axis grid lines |
| Optional |
| Show X axis labels |
| Optional |
| Show X axis ticks |
| Optional |
| Y axis type |
| Optional |
| Y axis position |
| Optional |
| Y axis title |
| Optional |
| Show Y axis grid lines |
| Optional |
| Show Y axis labels |
| Optional |
| Show Y axis ticks |
| Optional |
generate_sankey_chart
Generates Sankey diagrams.
Parameter | Description | Type | Required |
| Data object array |
| Yes |
| Source node field |
| Yes |
| Target node field |
| Yes |
| Value field |
| Yes |
generate_heatmap_chart
Generates heatmaps, suitable for displaying data density and distribution.
Parameter | Description | Type/Options | Required |
| Data object array |
| Yes |
| X axis field name |
| Yes |
| Y axis field name |
| Yes |
| Value field name |
| Yes |
| X axis type |
| Optional |
| X axis position |
| Optional |
| X axis title |
| Optional |
| Show X axis grid lines |
| Optional |
| Show X axis labels |
| Optional |
| Show X axis ticks |
| Optional |
| Y axis type |
| Optional |
| Y axis position |
| Optional |
| Y axis title |
| Optional |
| Show Y axis grid lines |
| Optional |
| Show Y axis labels |
| Optional |
| Show Y axis ticks |
| Optional |
Usage
To use in desktop applications (such as Trae, Claude, VSCode, Cline, Cherry Studio, Cursor, etc.), add the following MCP server configuration:
MacOS
{
"mcpServers": {
"vchart-mcp-server": {
"command": "npx",
"args": ["-y", "@visactor/vchart-mcp-server"]
}
}
}Windows
{
"mcpServers": {
"vchart-mcp-server": {
"command": "cmd",
"args": ["/c", "npx", "-y", "@visactor/vchart-mcp-server"]
}
}
}Installing via Smithery
To install vchart-mcp-server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @VisActor/vchart-mcp-server --client claudeRunning with SSE or Streamable Transport
Install and Start
Install @visactor/vchart-mcp-server globally:
npm install -g @visactor/vchart-mcp-serverStart the server:
# For SSE transport (default endpoint: /sse)
mcp-server-chart --transport sse
# For Streamable transport (default endpoint: /streamable)
mcp-server-chart --transport streamableThen you can access the server at:
SSE transport:
http://localhost:3001/sseStreamable transport:
http://localhost:3001/streamable
Other CLI Options
Options:
-t, --transport <type> Transport type (stdio, sse, streamable) [default: stdio]
-p, --port <port> Port number for HTTP-based transports [default: 3000]
-e, --endpoint <path> Endpoint path for HTTP-based transports [default: /message]
-h, --help Show this help message
Examples:
node index.js # Start with stdio transport
node index.js -t sse -p 3000 # Start with SSE transport on port 3000
node index.js -t sse -p 3000 -e /api/sse # Start with SSE transport on custom endpoint
node index.js -t streamable -p 3001 -e /stream # Start with streamable transport on custom endpointExample Usage in AI Conversations
Once configured, you can ask your AI assistant to create charts:
"Create an area chart showing monthly sales data"
The assistant will use the generate_cartesian_chart tool with parameters:
- chartType: "area"
- dataTable: your sales data
- xField: "month"
- yField: "sales""Generate a dual-axis chart comparing revenue and user growth"
The assistant will use the generate_dual_axis_chart tool with parameters:
- dataTable: your business data
- xField: "time"
- yField: ["revenue", "userGrowth"]"Show me an interactive HTML bar chart of quarterly performance"
The assistant will use the generate_cartesian_chart tool with parameters:
- chartType: "bar"
- dataTable: your quarterly data
- xField: "quarter"
- yField: "performance"
- output: "html""Create a pie chart of product sales share"
The assistant will use the generate_polar_chart tool with parameters:
- chartType: "pie"
- dataTable: your sales data
- categoryField: "product"
- valueField: "sales""Draw a scatter plot of height and weight"
The assistant will use the generate_scatter_chart tool with parameters:
- dataTable: your body data
- xField: "height"
- yField: "weight"
- colorField: "gender" (optional)"Create a radar chart for team skill assessment"
The assistant will use the generate_polar_chart tool with parameters:
- chartType: "radar"
- dataTable: your assessment data
- categoryField: "skill"
- valueField: "score""Generate a Sankey diagram showing data flow"
The assistant will use the generate_sankey_chart tool with parameters:
- dataTable: your flow data
- sourceField: "from"
- targetField: "to"
- valueField: "amount""Create a heatmap showing data distribution"
The assistant will use the generate_heatmap_chart tool with parameters:
- dataTable: your distribution data
- xField: "x_category"
- yField: "y_category"
- sizeField: "value"Development
Prerequisites
Node.js version >= 22.7.5
Build
npm run buildDevelopment Mode (Auto Rebuild)
npm run watchTesting
# Test chart generation
npm run test-tool
# Run MCP Inspector for debugging
npm run inspectorDebugging
Since the MCP server communicates via stdio, debugging can be challenging. Use MCP Inspector for development:
npm run inspectorTesting in AI Editors
To test the MCP server in an AI editor, use the following configuration:
{
"mcpServers": {
"vchart-mcp-server": {
"command": "node",
"args": ["/Users/path/to/your/project/vchart-mcp-server/build/index.js"]
}
}
}Environment Variables
VIMD_IMAGE_SERVER- Custom image generation server URL (default: https://vmind.visactor.com/export)
Private Deployment
Currently, images and HTML generated by vchart-mcp-server are produced via https://vmind.visactor.com/export. For private deployment, set the VIMD_IMAGE_SERVER environment variable to specify your own image generation server.
{
"mcpServers": {
"mcp-server-chart": {
"command": "npx",
"args": [
"-y",
"@visactor/vchart-mcp-server"
],
"env": {
"VIMD_IMAGE_SERVER": "<YOUR_VIS_REQUEST_SERVER>"
}
}
}
}Image generation service can be deployed privately refer to https://github.com/VisActor/vchart-mcp-server-export.
Star History
License
MIT License
Contributing
Contributions are welcome! Please feel free to submit issues and pull requests.
Related Projects
VChart - Underlying visualization library
Model Context Protocol - Protocol specification
Available Tools
10 toolsgenerate_cartesian_chartB
Generates Cartesian charts: line (trends over time), area (cumulative totals), bar (category comparison), waterfall (incremental changes), ranking bar (ordered categories), and funnel (visualizes stages in a process or conversion rates).
Inputs: chartType (required), dataTable (required), xField (required), yField (required), +25 more.
generate_dual_axis_chartA
Generate a dual-axis chart for visualizing two quantitative variables using a combination of bar and line series. Ideal for comparing trends and magnitudes across two metrics with distinct y-axes.
Inputs: dataTable (required), xField (required), yField (required), output, +23 more.
generate_heatmap_chartB
Generates a heatmap chart based on a Cartesian coordinate system. It is used to visualize the intensity or density of values at the intersection of two discrete variables, suitable for revealing association patterns and distribution characteristics between variables.
Inputs: dataTable (required), xField (required), yField (required), sizeField (required), +22 more.
generate_hierarchical_chartC
Generate a chart for hierarchical visualization of multi-level categorical data proportions, include sunburst, treemap, circle_packing.
Inputs: chartType (required), dataTable (required), colorField (required), valueField (required), +9 more.
generate_polar_chartC
Generate a polar chart (rose, radar, pie) to display numerical differences among different categories using radius and angle in polar coordinates.
Inputs: dataTable (required), chartType (required), categoryField (required), valueField (required), +22 more.
generate_progress_chartB
Generates a progress chart for visualizing quantitative values normalized between 0 and 1. Ideal for representing progress, completion rates, or proportional metrics. The gauge chart and liquid chart currently only supports displaying data for a single dimension.
Inputs: dataTable (required), chartType (required), valueField (required), output, +9 more.
generate_range_column_chartB
Generate a range column chart to display the value range (such as minimum and maximum) for each category, suitable for comparing the range distribution across different categories.
Inputs: dataTable (required), xField (required), yField (required), output, +21 more.
generate_sankey_chartC
Generate a Sankey diagram to visualize the flow relationships between nodes in complex networks, suitable for displaying the distribution and flow paths of source and target data.
Inputs: dataTable (required), sourceField (required), targetField (required), valueField (required), +9 more.
generate_scatter_chartB
Generate a scatter chart to visually display the distribution, clustering trends, and correlations of data points in two-dimensional or multi-dimensional space. Suitable for analyzing relationships between variables, outlier detection, and similar scenarios.
Inputs: dataTable (required), xField (required), yField (required), output, +22 more.
generate_wordcloud_vennC
Generate a word cloud to visualize word frequency or importance, or a Venn diagram to show relationships such as intersections and unions between sets.
Inputs: chartType (required), dataTable (required), colorField (required), valueField (required), +9 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 10 tools
Each tool is clearly distinct, targeting a specific chart type or visualization method (e.g., Cartesian, heatmap, hierarchical, Sankey). The descriptions precisely differentiate purposes, such as trend analysis for Cartesian charts versus flow relationships for Sankey diagrams, leaving no ambiguity for selection.
All tool names follow a consistent verb_noun pattern with 'generate_' as the prefix (e.g., generate_cartesian_chart, generate_heatmap_chart). This uniform naming convention makes the tool set predictable and easy to navigate for agents.
With 10 tools, the server is well-scoped for chart generation, covering a comprehensive range of visualization types from basic charts like scatter and bar to specialized ones like Sankey and word clouds. Each tool earns its place without redundancy or excessive bloat.
The tool set provides complete coverage for data visualization, including common chart types (Cartesian, scatter, polar), specialized visualizations (heatmap, hierarchical, Sankey), and utility charts (progress, word cloud/Venn). There are no obvious gaps; agents can handle diverse visualization needs without dead ends.
Related MCP Connectors
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
MCP server for AI dialogue using various LLM models via AceDataCloud
A Model Context Protocol server for Wix AI tools
MCP server for GLM chat completions using Zhipu AI models via AceDataCloud
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceA Model Context Protocol (MCP) server implementation that provides the LLM an interface for visualizing data using Vega-Lite syntax.100-
- TypeScriptMIT

MCP Server AntVofficial
AlicenseAqualityCmaintenanceA Model Context Protocol server that provides AntV visualization library documentation and code examples to AI assistants, supporting G2, G6, and F2 libraries for data visualization workflows.2134 npm40MIT- AlicenseNot gradedqualityCmaintenanceAn MCP (Model Context Protocol) server that enables LLMs to generate ECharts visualizations by accepting chart type, data and parameters and returning cloud image URLs of the generated charts.88Apache 2.0