Server facts
MCP Server Chart
Project
- Author
- antvis
- Repository
- github.com/antvis/mcp-server-chart
- License
- MIT
- Category
- Data & Analytics
Tech
- Runtime / language
- nodeTypeScript
- Transports
- stdio
- Remote available
- No
- Authentication
- Not specified
Activity
- GitHub stars
- 4,400
- Last commit
- Data as of
Tags
- Antv
- Charts
- Data Visualization
- Diagrams
- Pivot Tables
Overview
MCP Server Chart brings AntV visualization generation into assistant workflows. Its tool catalog covers familiar line, bar, column, area, pie, and scatter charts alongside statistical distributions, funnels, Sankey flows, treemaps, and radar views. Diagram tools represent processes, organizational structures, causes, and relationships. A spreadsheet tool renders ordinary tables or pivot tables depending on the supplied fields. Geographic tools add district distributions, point locations, and routes, although the README limits their map coverage to China through AMap.
The server is implemented in TypeScript and can be launched with npx for a local desktop client. Stdio is the default, while SSE and Streamable HTTP support network connections; Docker deployment is also documented. Rendering uses a free chart service by default. Users needing private processing can point the server to a separate rendering service through VIS_REQUEST_SERVER, with GPT-Vis-SSR offered as a deployment option. That private rendering path does not currently support the three geographic visualization tools. Tool filtering lets users disable selected chart generators, which can reduce the exposed surface or work around client compatibility problems. Generation history is another optional service configured with a service identifier. Without that setup, the README says users need to save their own results. These choices distinguish rendering configuration from the assistant-facing tool interface.
Install & configure
Requirements
- Node.js with npx for local execution
- An MCP-compatible client
npx -y @antv/mcp-server-chartThe README gives this desktop stdio configuration. Windows uses a cmd /c wrapper. Optional environment settings support private rendering, generation records, and disabled tools.
Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.
Config file · macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Use Settings → Developer → Edit Config when available. Do not assume a Linux configuration path; check the client documentation for your platform. Remote servers use the app’s connector flow when supported, not the local stdio file shown here. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"mcp-server-chart": {
"command": "npx",
"args": [
"-y",
"@antv/mcp-server-chart"
],
"env": {}
}
}
}Config file · Project: .cursor/mcp.json
User: ~/.cursor/mcp.json
The project path is relative to the workspace root. The tilde denotes your user home directory. Use Cursor’s MCP settings to confirm which configuration and scope your installed version is reading. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"mcp-server-chart": {
"command": "npx",
"args": [
"-y",
"@antv/mcp-server-chart"
],
"env": {}
}
}
}Config file · Workspace: .vscode/mcp.json
For user scope, use the “MCP: Open User Configuration” command if available. Do not guess a user configuration path across operating systems, profiles, containers, or remote workspaces; check the client documentation. Merge this example with existing settings; do not overwrite unrelated servers.
{
"servers": {
"mcp-server-chart": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@antv/mcp-server-chart"
],
"env": {}
}
}
}Config file · macOS/Linux: ~/.codeium/windsurf/mcp_config.json
Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json
Open the MCP configuration through Windsurf’s settings when possible to confirm the active file. Paths can differ in managed or future releases; check the client documentation if this location is not present. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"mcp-server-chart": {
"command": "npx",
"args": [
"-y",
"@antv/mcp-server-chart"
],
"env": {}
}
}
}Config file · Project scope: .mcp.json at the repository root
The project file uses mcpServers. For user scope, use claude mcp add --scope user rather than assuming .mcp.json in your home directory is the user configuration. Check the client documentation for managed settings and storage details. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"mcp-server-chart": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@antv/mcp-server-chart"
],
"env": {}
}
}
}Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.
Tools
Source: repository tool metadata. Tool descriptions are a documented snapshot, not a live capability check.
| Tool | What it does |
|---|---|
| generate_area_chart | Render a filled trend chart for values over a continuous axis. |
| generate_bar_chart | Compare category values with horizontal bars. |
| generate_boxplot_chart | Summarize distributions using medians, quartiles, and outliers. |
| generate_column_chart | Compare category values with vertical columns. |
| generate_district_map | Visualize values across administrative regions within supported map coverage. |
| generate_dual_axes_chart | Combine series with different units or scales in one chart. |
| generate_fishbone_diagram | Organize possible causes around a central problem. |
| generate_flow_diagram | Show process steps and decision paths. |
| generate_funnel_chart | Illustrate how values decrease across successive stages. |
| generate_histogram_chart | Display the frequency of observations grouped into intervals. |
| generate_line_chart | Plot changing values across time or another continuous dimension. |
| generate_liquid_chart | Show a percentage as a liquid-style fill indicator. |
| generate_mind_map | Arrange a central topic and its subtopics in branching form. |
| generate_network_graph | Visualize entities and the connections between them. |
| generate_organization_chart | Represent an organization's reporting hierarchy. |
| generate_path_map | Plot a planned route across supported map locations. |
| generate_pie_chart | Show how categories contribute to a whole. |
| generate_pin_map | Mark the positions and distribution of locations on a map. |
| generate_radar_chart | Compare multiple dimensions using a radial layout. |
| generate_sankey_chart | Show flows and their magnitudes between stages or categories. |
| generate_scatter_chart | Plot paired variables to inspect association and data patterns. |
| generate_treemap_chart | Represent hierarchical values using nested rectangles. |
| generate_venn_chart | Show overlaps and distinctions between sets. |
| generate_violin_chart | Compare category distributions with density-shaped statistical plots. |
| generate_waterfall_chart | Show how sequential positive and negative changes produce a final value. |
| generate_word_cloud_chart | Size words according to their frequency or weight. |
| generate_spreadsheet | Render a regular table, or a pivot table when grouping or value fields are supplied. |
Names, permissions, and defaults can change. Check the current upstream documentation before granting access.
Use cases
- Generate comparison and trend charts from structured data.
- Visualize distributions with histograms, boxplots, or violin plots.
- Create flow diagrams, organization charts, and relationship graphs.
- Render tables or pivot tables for summaries.
- Generate supported China-focused geographic visualizations.
Strengths
- Provides a wide range of chart, diagram, and table tools.
- Supports stdio, SSE, and Streamable HTTP.
- Allows private rendering service configuration and selective tool disabling.
Limitations
- Geographic generation is limited to China.
- The private rendering option does not support geographic tools.
- Generation history requires optional service-identifier setup; otherwise results must be saved manually.
Frequently asked questions
Independent listing, not an affiliation or security review. Grant the least access needed and verify the upstream instructions before running code.
