Moodle MCP Server
An MCP server that enables LLMs to interact with the Moodle platform to manage courses, students, assignments, and quizzes.
README
Moodle MCP Server
An MCP (Model Context Protocol) server that enables LLMs to interact with the Moodle platform to manage courses, students, assignments, and quizzes.
Features
Student Management Tools
list_students- Retrieves the list of students enrolled in the course- Displays ID, name, email, and last access time for each student
Assignment Management Tools
get_assignments- Retrieves all available assignments in the course- Includes information such as ID, name, description, due date, and maximum grade
get_student_submissions- Examines a student's submissions for a specific assignment- Requires the assignment ID and optionally the student ID
provide_assignment_feedback- Provides grades and comments for a student's submission- Requires student ID, assignment ID, grade, and feedback comment
Quiz Management Tools
get_quizzes- Retrieves all available quizzes in the course- Includes information such as ID, name, description, opening/closing dates, and maximum grade
get_quiz_attempts- Examines a student's attempts on a specific quiz- Requires the quiz ID and optionally the student ID
provide_quiz_feedback- Provides comments for a quiz attempt- Requires the attempt ID and feedback comment
Requirements
- Node.js (v14 or higher)
- Moodle API token with appropriate permissions
- Moodle course ID
Installation
- Clone this repository:
git clone https://github.com/your-username/moodle-mcp-server.git
cd moodle-mcp-server
- Install dependencies:
npm install
- Create a
.envfile with the following configuration:
MOODLE_API_URL=https://your-moodle.com/webservice/rest/server.php
MOODLE_API_TOKEN=your_api_token
MOODLE_COURSE_ID=1 # Replace with your course ID
- Build the server:
npm run build
Usage with Claude
To use with Claude Desktop, add the server configuration:
On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"moodle-mcp-server": {
"command": "/path/to/node",
"args": [
"/path/to/moodle-mcp-server/build/index.js"
],
"env": {
"MOODLE_API_URL": "https://your-moodle.com/webservice/rest/server.php",
"MOODLE_API_TOKEN": "your_moodle_api_token",
"MOODLE_COURSE_ID": "your_course_id"
},
"disabled": false,
"autoApprove": []
}
}
}
For Windows users, the paths would use backslashes:
{
"mcpServers": {
"moodle-mcp-server": {
"command": "C:\\path\\to\\node.exe",
"args": [
"C:\\path\\to\\moodle-mcp-server\\build\\index.js"
],
"env": {
"MOODLE_API_URL": "https://your-moodle.com/webservice/rest/server.php",
"MOODLE_API_TOKEN": "your_moodle_api_token",
"MOODLE_COURSE_ID": "your_course_id"
},
"disabled": false,
"autoApprove": []
}
}
}
Once configured, Claude will be able to interact with your Moodle course to:
- View the list of students and their submissions
- Provide comments and grades for assignments
- Examine quiz attempts and offer feedback
Development
For development with auto-rebuild:
npm run watch
Debugging
MCP servers communicate through stdio, which can make debugging challenging. We recommend using the MCP Inspector:
npm run inspector
The Inspector will provide a URL to access debugging tools in your browser.
Obtaining a Moodle API Token
- Log in to your Moodle site as an administrator
- Go to Site Administration > Plugins > Web Services > Manage tokens
- Create a new token with the necessary permissions to manage courses
- Copy the generated token and add it to your
.envfile
Security
- Never share your
.envfile or Moodle API token - Ensure the MCP server only has access to the courses it needs to manage
- Use a token with the minimum necessary permissions
License
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。