FAST-NUCES Flex Student Portal MCP Server
Connects AI assistants to the FAST-NUCES Flex Student Portal, enabling students to query their academic data including attendance, marks, transcript, and fee reports through natural language conversations.
README
FAST-NUCES flex Student Portal MCP Server
An MCP server that connects AI assistants like Claude Desktop or GitHub Copilot directly to your Flex Student Portal. Ask questions about your academic data in plain English.
What Can You Do?
Once connected, just chat naturally:
| Ask This | Get This |
|---|---|
| "Roast my transcript" | A brutally honest AI review of your transcript |
| "Am I passing PF?" | Quick calculation of your current standing |
| "How many classes did I bunk?" | Attendance reality check |
| "Compare my marks to class average" | See where you stand vs classmates |
Requirements
- Python 3.11+
- Google Chrome installed (for login automation)
- Claude Desktop or GitHub Copilot (with MCP support)
Installation
-
Clone and install dependencies:
git clone <repo-url> cd FLEX pip install -r requirements.txt -
Create
.envfile with your credentials:FLEX_ROLL_NO=22F-XXXX FLEX_PASSWORD=your_password -
Configure your MCP client:
<details> <summary><b>Claude Desktop</b></summary>
Edit
%APPDATA%\Claude\claude_desktop_config.json:{ "mcpServers": { "flex": { "command": "python", "args": ["C:/path/to/FLEX/server.py"], "env": { "FLEX_ROLL_NO": "22F-XXXX", "FLEX_PASSWORD": "your_password" } } } }</details>
<details> <summary><b>GitHub Copilot</b></summary>
Add to your MCP settings:
{ "flex": { "command": "python", "args": ["C:/path/to/FLEX/server.py"] } }</details>
Usage
- Start your MCP client (Claude Desktop / Copilot)
- The first time, say "Login to FLEX" ,Chrome will open for CAPTCHA
- If image CAPTCHA appears, solve it manually (you have 2 minutes)
- Once logged in, ask away!
Available Tools
| Tool | Description |
|---|---|
login |
Opens Chrome for CAPTCHA-authenticated login |
get_attendance |
Fetches attendance for all courses |
get_marks |
Gets detailed marks with class statistics |
get_transcript |
Full academic transcript with GPAs |
get_mca |
Modified Class Average for relative grading |
get_courses |
Current semester registered courses |
get_fee_report |
Payment history and fee details |
check_login_status |
Verify if session is active |
Project Structure
FLEX/
├── server.py # MCP entry point
├── auth.py # Login & session management
├── tools/ # MCP tool implementations
│ ├── login.py
│ ├── attendance.py
│ ├── marks.py
│ ├── transcript.py
│ ├── mca.py
│ ├── courses.py
│ ├── fees.py
│ └── status.py
└── parsers/ # HTML parsing logic
├── attendance.py
├── marks.py
├── transcript.py
├── courses.py
├── fees.py
└── challan.py
Notes
- Login session persists until you restart the MCP server
- Chrome must be installed (Other browsers are not supported, well if you can add support please do)
- Your credentials are only used locally, never transmitted elsewhere
- Image CAPTCHAs require manual solving, the browser stays open for you
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。