Kadmia MCP Server

Kadmia MCP Server

Integrates Kadmia's JavaScript learning platform with AI assistants to provide personalized explanations and track learning progress.

Category
访问服务器

README

Kadmia MCP Server

A Model Context Protocol (MCP) server for integrating the Kadmia JavaScript learning platform with AI assistants like Claude Code, Cursor, and others.

Prerequisites

Quick Start

1. Get your Kadmia credentials

Log into Kadmia to get your Firebase UID and API Key.

2. Configure Claude Code

Open your terminal and edit the Claude config file:

# macOS/Linux
nano ~/.claude.json

# Windows
notepad %USERPROFILE%\.claude.json

Add the following (replace the placeholder values with your credentials from Kadmia):

{
  "mcpServers": {
    "kadmia": {
      "command": "npx",
      "args": ["-y", "kadmia-mcp"],
      "env": {
        "KADMIA_LEARNER_ID": "your-firebase-uid-here",
        "KADMIA_API_KEY": "your-api-key-here"
      }
    }
  }
}

Alternative: Use the /mcp command inside Claude Code to add the server interactively.

3. Configure Cursor (Alternative)

  1. Open Cursor and go to Settings (gear icon) → MCP
  2. Click Add Server and enter:
    • Command: npx -y kadmia-mcp
    • Environment variables:
      • KADMIA_LEARNER_ID=your-firebase-uid-here
      • KADMIA_API_KEY=your-api-key-here

4. Verify It Works

Restart Claude Code or Cursor, then ask:

"Use the Kadmia explain_concept tool to explain closures"

If configured correctly, you'll get a personalized explanation based on your Kadmia skill level.

Environment Variables

Variable Required Description
KADMIA_LEARNER_ID Yes Your Firebase UID from thekadmia.com/kadmia-mcp
KADMIA_API_KEY Yes Your API key from thekadmia.com/kadmia-mcp
KADMIA_API_BASE No API base URL (default: Kadmia staging API)

Available Tools

get_learner_progress

Get your learning progress from Kadmia (requires authentication).

Parameter Type Required Description
No input required

Output: Progress data including subjects, recent activity, and learning insights.


explain_concept

Explain a JavaScript concept at your skill level. Returns an explanation tailored to your Kadmia progress with examples, common mistakes, and links to relevant lessons.

Parameter Type Required Description
concept string Yes The JavaScript concept to explain (e.g., "closures", "event loop", "prototype chain")
code_context string No Code snippet to make the explanation more relevant
depth "brief" | "standard" | "deep" No How detailed the explanation should be (default: "standard")

How It Works

The Kadmia MCP server creates a bridge between your coding environment and the Kadmia learning app:

┌─────────────────┐                    ┌─────────────────┐
│   IDE/Coding    │                    │   Kadmia App    │
│                 │   ──── MCP ────►   │                 │
│  • Explanations │                    │  • Skill levels │
│  • Progress     │   ◄──── MCP ────   │  • Mastery data │
└─────────────────┘                    └─────────────────┘
  • Explanations are tailored to your skill level from Kadmia
  • Progress data personalizes your learning experience

Future Tools

  • bookmark_concept — Save concepts to study later in the Kadmia app
  • generate_challenge — Get coding challenges calibrated to your skill level
  • js_comedy_hour — Hear the JS joke of the day

Development

# Run with auto-reload
npm run dev

# Build TypeScript
npm run build

# Run the server
npm start

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选