clearpath-learning-mcp
A learning MCP server that transforms technical topics into four structured parts: definition, analogy, example, and hands-on try-it exercises, enabling beginner-friendly study directly from any MCP client.
README
ClearPath Learning MCP
ClearPath Learning MCP is a beginner-first technical learning project. It ships a public website, a hosted learner workspace, and a standalone MCP package that turns a technical topic into four useful parts: What it is, Real-world analogy, Example, and Try it.
The project is designed for people learning Python, security, DevOps, web development, databases, networking, and related subjects. Security lessons are intentionally constrained to defensive, lawful, locally authorized learning examples.
Project map
| Area | Purpose |
|---|---|
client/ |
Public MCP product website and authenticated learner interface. |
server/ |
GPT-5 mini lesson engine, private lesson history, hosted MCP routes, and optional reminder flow. |
packages/clearpath-learning-mcp/ |
The publishable local MCP package using standard input/output transport. |
docs/ |
Release and open-source maintenance guidance. |
Quick start
Use Node.js 20 or later and pnpm 10 or later.
pnpm install
pnpm dev
The public product site is available at /, while the hosted learner is at /learn. Run the verification suite before opening a pull request:
pnpm check
pnpm test
Local MCP package
The standalone package is located in packages/clearpath-learning-mcp. It is intentionally separate from the hosted website so developers can install and run it from any MCP-compatible desktop client or project. After publication, users can install it with npm install clearpath-learning-mcp.
Install from npm
Install the published MCP package in a project:
npm install clearpath-learning-mcp
Or let an MCP-compatible client start the current package through npx:
npx -y clearpath-learning-mcp
Use the package README for the complete MCP-client configuration, including the locally supplied provider key.
Install directly from GitHub
Users do not need an npm token to use ClearPath from this repository. Clone the project, build the local MCP package, and add its command to an MCP-compatible client. The full copy-and-paste guide is available in Using ClearPath from GitHub.
cd packages/clearpath-learning-mcp
npm install
npm run build
npm test
The local package requires each user to configure their own OpenAI-compatible provider key. See the package README and the configuration reference for the complete client configuration example. Never commit provider keys, test credentials, or .env files.
Open-source community
This project is distributed under the MIT License. Please read the contribution guide, code of conduct, and security policy before participating.
Release ownership
The package metadata links to this public repository. Before publishing a version, maintainers should complete the npm publishing guide and the release checklist. Only maintainers publishing to npm need an npm token; end users cloning or installing ClearPath do not.
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。