amCharts 5 MCP Server
MCP server that gives AI assistants on-demand access to 1,500+ amCharts 5 docs, ~300 code examples, and 1000+ class API references.
README
amCharts 5 MCP Server
An MCP (Model Context Protocol) server that gives AI assistants on-demand access to the complete amCharts 5 knowledge base: 141 documentation pages, 283 code examples, and 1,098 class API references.
Works with Claude Code, Claude Desktop, Cursor, Windsurf, VS Code + GitHub Copilot, and any other MCP-compatible AI tool.
Why?
Instead of loading the entire amCharts reference into the AI's context window, the MCP server lets the AI query exactly what it needs — a specific chart type reference, a code example, or an API lookup. This means better answers with less context waste.
Quick Start
Claude Code
For all projects (global, recommended):
claude mcp add -s user amcharts5 -- npx -y @amcharts/amcharts5-mcp
For current project only:
claude mcp add amcharts5 -- npx -y @amcharts/amcharts5-mcp
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"amcharts5": {
"command": "npx",
"args": ["-y", "@amcharts/amcharts5-mcp"]
}
}
}
Cursor
Create or edit .cursor/mcp.json in your project root (or ~/.cursor/mcp.json for global):
{
"mcpServers": {
"amcharts5": {
"command": "npx",
"args": ["-y", "@amcharts/amcharts5-mcp"]
}
}
}
Windsurf
Edit ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"amcharts5": {
"command": "npx",
"args": ["-y", "@amcharts/amcharts5-mcp"]
}
}
}
VS Code + GitHub Copilot
Create or edit .vscode/mcp.json in your workspace:
{
"servers": {
"amcharts5": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@amcharts/amcharts5-mcp"]
}
}
}
Other MCP-compatible tools
For any other tool that supports MCP (Cline, Continue, Amazon Q, Zed, etc.), configure it to run:
npx -y @amcharts/amcharts5-mcp
Run locally (for development)
git clone https://github.com/amcharts/amcharts5-mcp.git
cd amcharts5-mcp
npm install
npm start
Available Tools
| Tool | Description |
|---|---|
get_core_reference |
Get core amCharts 5 docs — setup, themes, colors, events, common pitfalls |
get_chart_reference |
Get full reference for a chart type (e.g. "pie", "sankey", "xy") |
list_chart_types |
List all available chart types and their keywords |
search_docs |
Search the skill reference docs by keyword |
search_all |
Search across everything — skill docs, full documentation, and code examples |
get_doc |
Get a full documentation page (e.g. "charts/xy-chart/axes", "concepts/events") |
get_section |
Get a specific section from a reference file by heading |
get_quick_start |
Get a minimal working template for any chart type |
list_examples |
Browse all 283 examples, optionally filtered by category |
get_example |
Get the full code for a specific example |
Example Usage
Once connected, your AI assistant can:
- "Build me a pie chart" → AI calls
get_quick_start("pie")and adapts the template - "How do I format date axis labels?" → AI calls
search_all("date axis label format") - "Show me the Sankey diagram example" → AI calls
get_example("examples/flow/sankey-diagram") - "What settings does XYChart support?" → AI calls
get_doc("reference/xychart") - "How do I integrate with React?" → AI calls
get_doc("getting-started/integrations/react") - "What chart types are available?" → AI calls
list_chart_types()
Content
The server includes 1,500+ documents:
- 141 documentation pages — getting started, chart guides, concepts (themes, events, adapters, data binding, animations, accessibility, etc.), and framework integration guides (React, Angular, Vue, Next.js, Svelte, and more)
- 283 code examples — working demos across 16 categories including column/bar, line/area, pie/donut, maps, hierarchy, flow, radar/polar, stock, gauges, Gantt, timeline, and more
- 1,098 class API references — every class in the amCharts 5 library with its settings, properties, methods, events, and inheritance chain
- Curated skill reference — quick-start templates and chart-specific guides from the amCharts 5 AI Skill
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。