juno-mcp
Enables LLMs to interact with MGMU Juno ERP, providing tools to fetch student profile, attendance, fees, schedule, results, and search students.
README
Juno ERP MCP Client
A modular Model Context Protocol (MCP) server for interacting with MGMU Juno ERP. This client exposes various student-related data as tools for use with LLMs (like Claude).
🚀 Features
- Profile Management: Fetch student personal information and academic info.
- Attendance: Get detailed attendance records and visual graph data.
- Fees & Admission: Check remaining fees, fee structure, and admission details.
- Academics: Fetch today's schedule, exam results, and course lists for specific terms.
- Search: Search for students within the ERP.
🛠️ Setup
-
Install Dependencies:
npm install -
Configure Environment: Copy
.env.exampleto.envand fill in your credentials:cp .env.example .envEdit
.env:email=your_email@example.com password=your_password PORT=8987 -
Build the Project:
npm run build
🏃 Running the Server
Development Mode
Runs the server using tsx for live development:
npm run dev
Production Mode
Builds and runs the compiled JavaScript:
npm run build
npm start
The server will be available at http://localhost:8987/mcp.
🐳 Docker Support
The Docker image is automatically built and published to GHCR:
ghcr.io/danish-mar/juno-mcp:master
You can run the server using Docker and Docker Compose:
-
Build and Start:
docker-compose up -d --build -
Check Logs:
docker logs -f juno-mcp -
Stop:
docker-compose down
🛠️ Available Tools
| Tool | Description |
|---|---|
get_profile |
Fetch profile information for the logged-in student. |
get_academic_info |
Fetch academic information. |
get_attendance_details |
Fetch detailed attendance records. |
get_attendance_graph |
Fetch attendance graph data. |
get_today_schedule |
Fetch today's schedule for a specific date. |
get_student_results |
Fetch exam results (requires IDs). |
get_remaining_fees |
Fetch pending fee details. |
search_student |
Search for students by name. |
🔒 Security
- Credentials are never hardcoded and are loaded from
.env. .envis included in.gitignoreto prevent accidental exposure.- Session tokens are managed in-memory and refreshed automatically upon expiry.
📄 License
ISC
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。