A Model Context Protocol (MCP) server designed for AI development and QA that provides AntV documentation context and code examples using the latest APIs.

mcp-server-antv Technical Architecture

Supports G2, G6, and F2 libraries for declarative visualization workflows, with S2, X6, L7, and more (including AVA, ADC, and G) coming soon.

• ✅ AntV 5.x Compatibility: Leverages the latest APIs for performance and modularity.
• 🧩 Multi-Library Support: G2 (2D charts), G6 (graph/networks), and F2 (mobile charts).
• 🔍 Smart Intent Extraction: Detects library usage and task complexity via extract_antv_topic.
• 📚 Contextual Documentation: Fetches relevant AntV docs and code snippets with query_antv_document.

• Node.js >= v18.0.0
• Cursor, VSCode, Cline, Claude Desktop or another MCP Client.

Install MCP Server

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"]
 }
 }
}

Install in 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\"]}"

An example workflow:

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

MIT@AntV.