TechMCP - PSG College of Technology MCP Server
Enables AI assistants to access PSG College of Technology e-campus portal data including CA marks, attendance records, timetable schedules, and course information through natural language queries.
README
🎓 TechMCP - PSG College of Technology MCP Server
TechMCP is a comprehensive Model Context Protocol (MCP) server that seamlessly integrates with PSG College of Technology's e-campus portal. It provides AI assistants like Claude, Cursor, and Raycast with direct access to student academic data including CA marks, attendance records, and timetable information.
🚀 Server hosting coming soon! No more local setup required.
✨ Features
📊 CA Marks & Assessment Tools
- CA1 & CA2 Marks: Fetch continuous assessment marks for individual subjects or all subjects
- Assignment Marks: Get assignment scores for theory courses
- Tutorial Marks: Access tutorial marks and MPT scores
- Subject Search: Search by subject code or subject name
- Health Monitoring: Built-in health checks for scraper status
📅 Attendance Management
- Attendance Percentage: Real-time attendance tracking for all subjects
- Present/Absent Hours: Detailed hour-wise attendance breakdown
- Bunk Calculator: Smart calculation of available bunks while maintaining minimum attendance
- Subject-wise Analysis: Individual subject attendance details
- Attendance Alerts: Monitor attendance status across all courses
🕒 Smart Timetable System
- Live Schedule: Get current day's complete timetable
- Next Class: Find your immediate next class with location details
- Remaining Classes: See what's left for today
- Weekly Schedule: Complete week view with all subjects
- Break Schedule: Track break times and current break status
- Tomorrow's Schedule: Plan ahead with next day's timetable
- Day-specific Schedule: Get timetable for any day of the week
🎯 Course Management
- Course Directory: Complete list of all available courses
- Course Search: Find courses by code or name
- Detailed Course Info: Get comprehensive course details including timetable
- Subject Mapping: Automatic mapping between course codes and names
🔮 Coming Soon
- CGPA Calculator: Calculate current CGPA and predict future performance
- CA Schedule: Upcoming continuous assessment dates
- Semester Schedule: Important academic dates and deadlines
📋 Prerequisites
- Python 3.10+
- Valid PSG Tech e-campus credentials
- Internet connection for portal access
🚀 Installation
1. Clone the Repository
git clone https://github.com/codit04/TechMCP.git
cd TechMCP
2. Install Dependencies
pip install -r requirements.txt
3. Configure Credentials
⚠️ IMPORTANT: You must update the config.json file with your PSG Tech e-campus credentials:
{
"credentials": {
"roll_number": "YOUR_ACTUAL_ROLL_NUMBER",
"password": "YOUR_ACTUAL_PASSWORD"
},
"server": {
"host": "localhost",
"port": 8080,
"sse_mode": true
}
}
4. Start the Server
python server.py
The server will start on http://127.0.0.1:8080/sse and be ready for MCP connections.
🔗 Connecting to AI Assistants
🖱️ Cursor IDE
- Create the MCP configuration directory:
mkdir -p ~/.cursor
- Create
~/.cursor/mcp.jsonwith the following content:
{
"mcpServers": {
"techmcp": {
"url": "http://127.0.0.1:8080/sse",
"name": "TechMCP - PSG Tech Integration",
"transport":"sse"
}
}
}
- Restart Cursor IDE
- The server will appear in your MCP settings
- Start asking questions like: "What are my CA1 marks?" or "What's my next class?"
🤖 Claude Desktop
- Install the server locally:
# From the TechMCP directory
mcp install server.py
- Restart Claude Desktop
- The TechMCP server will be available in Claude's tools panel
- Ask Claude about your academic data directly!
⚡ Raycast
- Ensure the server is running on
http://127.0.0.1:8080/sse - Install a compatible MCP extension for Raycast
- Configure the server URL in Raycast settings
- Access your academic data through Raycast commands
🛠️ Available Tools
Marks & Assessment
get_ca1_subject_mark- Get CA1 mark for a specific subjectget_ca2_subject_mark- Get CA2 mark for a specific subjectget_ca1_all_marks- Get CA1 marks for all subjectsget_ca2_all_marks- Get CA2 marks for all subjectsget_assignment_mark_by_subject- Get assignment marks for a subjectget_all_assignment_marks- Get all assignment marksget_tutorial_marks_by_subject- Get tutorial marks for a subjectget_all_tutorial_marks- Get all tutorial markslist_available_subjects- List all available subjectshealth_check- Check scraper health status
Attendance Management
get_subject_attendance_percentage- Get attendance % for a subjectget_all_attendance_percentages- Get attendance % for all subjectsget_subject_absent_hours- Get absent hours for a subjectget_all_absent_hours- Get absent hours for all subjectsget_subject_present_hours- Get present hours for a subjectget_all_present_hours- Get present hours for all subjectsget_subject_available_bunks- Calculate available bunks for a subjectget_all_available_bunks- Calculate available bunks for all subjects
Timetable & Schedule
get_next_class- Get your next scheduled classget_todays_schedule- Get today's complete scheduleget_schedule_from_now- Get remaining classes for todayget_tomorrows_schedule- Get tomorrow's scheduleget_schedule_for_day- Get schedule for a specific dayget_weekly_schedule- Get complete weekly timetableget_break_schedule- Get break times and current status
Course Information
get_all_courses- Get list of all coursessearch_courses- Search courses by name or codeget_course_details- Get detailed course information
💡 Usage Examples
With Cursor/Claude
"What are my CA1 marks for Data Structures?"
"Show me my attendance percentage for all subjects"
"What's my next class?"
"How many hours can I bunk in Computer Networks while maintaining 75% attendance?"
"What's my complete schedule for tomorrow?"
Direct API Usage
# Get CA1 marks for a subject
curl -X POST http://127.0.0.1:8080/mcp \
-H "Content-Type: application/json" \
-d '{"method": "get_ca1_subject_mark", "params": {"subject": "20XTO1"}}'
🤝 Contributing
We welcome contributions to improve TechMCP! Here's how you can help:
- Fork the repository
- Create a feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
🐛 Issues & Suggestions
- GitHub Issues: Create an issue for bugs or feature requests
- Discord Community: Join our discussion at @discord.gg/fRFGPQKERJ
🙏 Acknowledgments
- @mathanamathav - Inspiration from the bunker-api project
- PSG College of Technology - For the excellent e-campus portal
- E-Campus Portal - The source of all academic data
⚖️ Legal & Privacy
- This project is for educational purposes only
- Uses your own credentials to access your own data
- No data is stored or transmitted to external servers
- Respects PSG Tech's e-campus terms of service
- Open source and transparent
📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
🔧 Technical Details
- Framework: FastMCP 2.0+
- Web Scraping: Beautiful Soup 4, httpx
- Data Models: Pydantic
- Transport: Server-Sent Events (SSE)
- Authentication: Session-based with CSRF protection
<div align="center">
Made with ❤️ for PSG Tech Students
Simplifying academic data access through AI
⭐ Star this repo | 🐛 Report Bug | 💬 Join Discord
</div>
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.