offline-mcp-educational-server
Enables generation of educational content like MCQs, lesson plans, and flashcards without relying on external LLMs, fully offline and compatible with Claude Desktop.
README
โ
README.md
# Offline MCP Server โ EduChain Assignment Submission
This project implements an **offline MCP (Meta-Channel Protocol) server** that simulates educational content generation tools without using any external LLMs (e.g., OpenAI or Gemini). It is fully compatible with Claude Desktop or can be tested independently using browser, Postman, or cURL.
---
## ๐ Project Structure
. โโโ run.py # Entry point to run the Flask server โโโ requirements.txt # Dependencies (Flask) โโโ claude_desktop_config.json # Claude Desktop configuration (optional) โโโ Sample_Responses.txt # Sample API calls and responses โโโ README.md # This file โโโ app/ โโโ init.py # Initializes the Flask app โโโ routes.py # Flask routes and UI form โโโ edu_utils.py # Core educational logic (MCQs, plans, flashcards)
---
## ๐ Features
| Tool | Endpoint | Description |
|------------------|--------------------------|-------------------------------------------------|
| MCQ Generator | `/generate-mcqs` | Generates MCQs based on topic and count |
| Lesson Plan Tool | `/get-lesson-plan` | Returns a structured lesson plan for a subject |
| Flashcards Tool | `/generate-flashcards` | Creates flashcards from topic keywords |
| Test UI | `/` | Browser form to test all routes easily |
---
## ๐ง LLM-Free Design
Instead of calling real LLMs like OpenAI or Gemini, this project:
- Uses **handwritten logic**
- Returns **realistic educational content**
- Fully mimics JSON structure expected by Claude Desktop
---
## ๐ง Installation & Run
### Step 1: Install requirements
```bash
pip install -r requirements.txt
Step 2: Run the Flask server
python run.py
By default, the server runs on:
http://localhost:5001
๐ Test the Server (Without Claude)
Visit in browser:
http://localhost:5001
Use the dropdowns and forms to test:
- Generate MCQs
- Get Lesson Plan
- Create Flashcards
Or use Postman / curl.
๐งช Sample Request
POST /generate-mcqs
{
"topic": "Python Basics",
"count": 2
}
Sample Response
{
"mcqs": [
{
"question": "Which keyword is used to define a function in Python?",
"options": ["define", "def", "func", "lambda"],
"answer": "def"
},
...
]
}
๐ Claude Desktop Integration (Optional)
Use the claude_desktop_config.json file provided to connect this server to Claude Desktop. Restart Claude Desktop after configuring it.
๐ฅ Submission Checklist
- [x]
mcp_server.pyโ now modular:run.py + routes.py + utils.py - [x]
claude_desktop_config.json - [x]
Sample_Responses.txt - [x]
README.md - [x] Uses NO LLMs (fully offline)
- [x] Tested via browser, Postman, and curl
๐ง Author
Nihal Jaiswal B.Tech (2026) GitHub: [github.com/yourusername]
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
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.