stepik-mcp
MCP server for managing Stepik courses, sections, lessons, units, and steps from any MCP-compatible client.
README
stepik-mcp
MCP server for managing Stepik courses from Claude Code, Cursor, or any MCP-compatible client.
20 Tools
| Category | Tools |
|---|---|
| Courses | stepik_list_courses, stepik_get_course, stepik_create_course, stepik_update_course, stepik_publish_course |
| Sections | stepik_get_sections, stepik_create_section, stepik_update_section, stepik_delete_section |
| Lessons | stepik_get_lessons, stepik_get_lesson, stepik_create_lesson, stepik_update_lesson, stepik_delete_lesson |
| Units | stepik_create_unit |
| Steps | stepik_get_steps, stepik_create_text_step, stepik_update_text_step, stepik_create_quiz_step |
| Health | stepik_health_check |
Quick Start
1. Get API Credentials
Go to stepik.org/oauth2/applications/ → Create application → Client type: Confidential, Grant type: Client credentials.
Copy the Client ID and Client Secret.
2. Install
git clone https://github.com/seniorcat/stepik-mcp.git
cd stepik-mcp
pip install mcp
Or with uv:
uv pip install mcp
3. Configure
Set environment variables:
export STEPIK_CLIENT_ID=your-client-id
export STEPIK_CLIENT_SECRET=your-client-secret
Or create a .env file next to the server script:
STEPIK_CLIENT_ID=your-client-id
STEPIK_CLIENT_SECRET=your-client-secret
(Requires pip install python-dotenv)
4. Add to Claude Code
Add to ~/.claude/settings.json:
{
"mcpServers": {
"stepik": {
"command": "python3",
"args": ["/path/to/stepik_mcp_server.py"],
"env": {
"STEPIK_CLIENT_ID": "your-client-id",
"STEPIK_CLIENT_SECRET": "your-client-secret"
}
}
}
}
5. Add to Cursor
Add to .cursor/mcp.json:
{
"mcpServers": {
"stepik": {
"command": "python3",
"args": ["/path/to/stepik_mcp_server.py"],
"env": {
"STEPIK_CLIENT_ID": "your-client-id",
"STEPIK_CLIENT_SECRET": "your-client-secret"
}
}
}
}
Course Hierarchy
Course
└── Section (Module 1, Module 2, ...)
└── Unit (binding)
└── Lesson
└── Step (text, video, quiz, ...)
Typical workflow for building a course:
stepik_create_course → get course_id
stepik_create_section → get section_id (repeat per module)
stepik_create_lesson → get lesson_id (repeat per lesson)
stepik_create_unit → attach lesson to section
stepik_create_text_step → add content to lesson
stepik_publish_course → make it visible
Usage Examples
Once connected, your AI assistant can manage Stepik courses directly:
"Создай новый курс 'Python для начинающих'"
"Покажи все мои курсы"
"Добавь раздел 'Основы' в курс 12345"
"Создай урок 'Переменные и типы данных' и добавь в раздел 67890"
"Добавь текстовый шаг с объяснением в урок 11111"
"Создай тест с 4 вариантами ответа"
"Опубликуй курс 12345"
Requirements
- Python 3.10+
- Stepik account with instructor access
mcpPython packagepython-dotenv(optional)
Notes
- Lesson titles are limited to 64 characters by the Stepik API (enforced automatically)
- Courses are created as drafts — use
stepik_publish_coursewhen ready - OAuth2 tokens are cached and refreshed automatically
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。