mcp-server-antv
Health Pass
- License รขโฌโ License: MIT
- Description รขโฌโ Repository has a description
- Active repo รขโฌโ Last push 0 days ago
- Community trust รขโฌโ 38 GitHub stars
Code Fail
- process.env รขโฌโ Environment variable access in __tests__/utils/env.spec.ts
- rm -rf รขโฌโ Recursive force deletion command in package.json
Permissions Pass
- Permissions รขโฌโ No dangerous permissions requested
This MCP server provides AI assistants with contextual documentation, API references, and code examples for the AntV visualization ecosystem (G2, G6, F2). It acts as a knowledge bridge to help developers generate accurate visualization code.
Security Assessment
The overall risk is Medium. The primary concern is a failed audit check for a recursive force deletion command (`rm -rf`) found in the `package.json` scripts. While this is commonly used for cleaning directories during the build process, it represents a potential supply-chain risk if the scripts are ever maliciously altered. A warning was also flagged for environment variable access, though this was isolated to a specific test file (`env.spec.ts`), making it a low threat. The tool does not request dangerous system permissions, and no hardcoded secrets were detected.
Quality Assessment
The project is in good health and actively maintained, with its most recent push occurring today. It is backed by the official AntV organization (under Ant Group/Alipay) and operates under the standard, permissive MIT license. Community trust is currently low but growing, as evidenced by its 38 GitHub stars. The codebase is written in TypeScript, which provides good standard practices and type safety.
Verdict
Use with caution โ while the tool is officially backed and useful, developers should quickly verify the `package.json` build scripts to ensure the `rm -rf` commands are strictly limited to safe cleanup operations before running.
๐ง๐ปโ๐ป MCP Server for @antvis visualization development, which provides documentation context and examples for visualization developers.
MCP Server AntV

A Model Context Protocol (MCP) server designed for AI development and QA that provides AntV documentation context and code examples using the latest APIs.
Supports G2, G6, and F2 libraries for declarative visualization workflows, with S2, X6, L7, and more (including AVA, ADC, and G) coming soon.
โจ Features
- โ AntV 5.x Compatibility: Leverages the latest APIs for performance and modularity.
- ๐งฉ Multi-Library Support: G2 (2D charts), G6 (graph/networks), and F2 (mobile charts).
- ๐ Smart Intent Extraction: Detects library usage and task complexity via
extract_antv_topic. - ๐ Contextual Documentation: Fetches relevant AntV docs and code snippets with
query_antv_document.
๐ ๏ธ Quick Start
Requirements
- Node.js >= v18.0.0
- Cursor, VSCode, Cline, Claude Desktop or another MCP Client.
Connect to Cursor
Go to: Settings -> Cursor Settings -> MCP -> Add new global MCP server
{
"mcpServers": {
"mcp-server-antv": {
"command": "npx",
"args": ["-y", "@antv/mcp-server-antv"]
}
}
}
On Window system:
{
"mcpServers": {
"mcp-server-antv": {
"command": "cmd",
"args": ["/c", "npx", "-y", "@antv/mcp-server-antv"]
}
}
}
Connect to VSCode
Pasting the following configuration into your VSCode ~/.vscode/mcp.json file is the recommended approach.
{
"servers": {
"mcp-server-antv": {
"command": "npx",
"args": ["-y", "@antv/mcp-server-antv"]
}
}
}
or command-line configuration
code --add-mcp "{\"name\":\"mcp-server-antv\",\"command\": \"npx\",\"args\": [\"-y\",\"@antv/mcp-server-antv\"]}"
๐งช Example Workflow
An example workflow:
๐งฐ Tools Overview
| Tool | Functionality |
|---|---|
extract_antv_topic |
Extract user intent, detects library (G2/G6/F2), and infers task complexity. |
query_antv_document |
fetch latest documentation and code examples with context7 |
๐จ Contributing
Clone the repo
git clone https://github.com/antvis/mcp-server-chart.git
cd mcp-server-chart
Install dependencies:
npm install
Build the server:
npm run build
Start the MCP server:
npm run start
๐ License
MIT@AntV.
Reviews (0)
Sign in to leave a review.
Leave a reviewNo results found