Classavo MCP Server

Classavo MCP Server

Enables AI assistants to interact with the Classavo education platform via natural language for course management, assignments, grading, attendance, polling, and discussions, with strict privacy controls for students.

Category
访问服务器

README

Classavo MCP Server

A Model Context Protocol (MCP) server that enables AI assistants like Claude Desktop to interact with the Classavo education platform via natural language.

Features

For Professors

  • Course Management - Create courses, manage rosters, invite students
  • Assignments - Create, update, clone assignments and quizzes
  • Grading - View submissions, grade work, provide feedback
  • Attendance - Start sessions, generate codes, track attendance
  • Live Polling - Create and run polls during class
  • Discussions - Create threads, pin comments, manage discussions
  • Analytics - View insights, export gradebook to LMS formats

For Students

  • View Grades - See YOUR grades (privacy protected)
  • Submit Work - Submit assignments
  • Attendance - Check in with attendance codes
  • Polling - Vote in active polls
  • Discussions - Participate in discussions
  • Content - View course chapters and materials

Privacy Controls

Important: This server implements strict privacy controls:

  • Students can ONLY view their own grades, submissions, and attendance
  • Student tools do not accept student_id parameters
  • API endpoints return only the authenticated user's data
  • Professor-only tools verify user role before execution

Installation

Prerequisites

  • Python 3.10+
  • A Classavo account (Professor or Student)

Setup

  1. Clone the repository:
git clone https://github.com/kiranprakashkm/classavo-mcp.git
cd classavo-mcp
  1. Create a virtual environment:
python3 -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate
  1. Install dependencies:
pip install -r requirements.txt

Configuration

Environment Variables

Create a .env file or set these environment variables:

# Classavo API URL (production or local)
CLASSAVO_API_URL=https://api.classavo.com

# Option 1: Pre-configured API token
CLASSAVO_API_TOKEN=your_token_here

# Option 2: Username/password for login flow
CLASSAVO_USERNAME=your_email@example.com
CLASSAVO_PASSWORD=your_password

# Optional settings
CLASSAVO_RATE_LIMIT=10  # Requests per second
DEBUG=false

Claude Desktop Configuration

Add to ~/.config/claude/claude_desktop_config.json (macOS/Linux) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "classavo": {
      "command": "python",
      "args": ["/path/to/classavo-mcp/main.py"],
      "env": {
        "CLASSAVO_API_URL": "https://api.classavo.com",
        "CLASSAVO_USERNAME": "your_email@example.com",
        "CLASSAVO_PASSWORD": "your_password"
      }
    }
  }
}

Alternatively, use an API token:

{
  "mcpServers": {
    "classavo": {
      "command": "python",
      "args": ["/path/to/classavo-mcp/main.py"],
      "env": {
        "CLASSAVO_API_URL": "https://api.classavo.com",
        "CLASSAVO_API_TOKEN": "your_api_token_here"
      }
    }
  }
}

Running the Server

Standalone

python main.py

With Claude Desktop

After configuring Claude Desktop, restart it. The Classavo tools will be available automatically.

Available Tools

Authentication

Tool Description
login Authenticate with username/password
logout End session
get_my_profile View current user info
get_notifications View notifications

Courses

Tool Description Access
list_courses List your courses All
get_course Get course details All
create_course Create a new course Professor
get_course_roster View enrolled students Professor
invite_students Invite students by email Professor
join_course Join with invite code Student
get_course_analytics View course insights Professor

Assignments

Tool Description Access
list_assignments List assignments All
get_assignment Get assignment details All
create_assignment Create assignment Professor
update_assignment Update assignment Professor
delete_assignment Delete assignment Professor
create_question Add question to assignment Professor
clone_assignment Clone to another course Professor

Grading & Submissions

Tool Description Access
list_submissions View all submissions Professor
get_submission View submission details Professor
grade_submission Grade a submission Professor
get_gradebook Full gradebook Professor
export_gradebook Export to LMS format Professor
view_my_grades Your grades only Student
view_my_submissions Your submissions only Student
submit_assignment Submit your work Student

Attendance

Tool Description Access
start_attendance_session Start attendance Professor
end_attendance_session End session Professor
get_active_sessions View active sessions Professor
get_attendance_report Attendance report Professor
mark_student_attendance Manual marking Professor
check_in_attendance Check in with code Student
view_my_attendance Your attendance Student

Polling

Tool Description Access
list_polls List polls Professor
create_poll Create a poll Professor
start_poll Launch poll Professor
end_poll End poll Professor
get_poll_results View results Professor
vote_in_poll Cast your vote Student
get_active_polls View active polls Student

Discussions

Tool Description Access
list_discussions List discussions All
get_discussion View discussion All
create_discussion Create thread Professor
post_comment Add comment All
pin_comment Pin comment Professor
delete_discussion Delete thread Professor

Search

Tool Description Access
global_search Search across courses All

Example Usage

Professor Examples

"List all my courses"
"Show the roster for Chemistry 101"
"Create a homework assignment called 'Chapter 5 Review' for course abc123"
"Start attendance for my Biology class"
"How did students do on the midterm exam?"
"Export grades to Canvas format"

Student Examples

"What are my grades in Chemistry?"
"Show my upcoming deadlines"
"Check me in with attendance code 1234"
"Submit my homework for assignment xyz"
"Vote option B in the current poll"

Development

Running Tests

pytest
pytest --cov=. --cov-report=term-missing

Project Structure

classavo-mcp/
├── main.py              # FastMCP server entry point
├── config.py            # Environment configuration
├── client.py            # Async HTTP client for Classavo API
├── auth.py              # Authentication management
├── tools/
│   ├── __init__.py      # Tool registration
│   ├── auth_tools.py    # Login, profile, notifications
│   ├── course_tools.py  # Course CRUD, roster
│   ├── assignment_tools.py  # Assignment management
│   ├── grading_tools.py     # Submissions, grading
│   ├── attendance_tools.py  # Attendance tracking
│   ├── polling_tools.py     # Live polls
│   ├── discussion_tools.py  # Discussion boards
│   └── student_tools.py     # Student-specific (privacy protected)
├── requirements.txt
├── README.md
└── PLAN.md

License

MIT License - See LICENSE file for details.

Support

For issues or questions:

  • Open an issue on GitHub
  • Contact the Classavo support team

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
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
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
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
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
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
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
mcp-server-qdrant

mcp-server-qdrant

这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。

官方
精选
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选