Gauntlet Incept
About
Integrates with QTI services and LLMs to generate personalized educational content tailored to students' knowledge levels and interests, streamlining the creation of adaptive learning materials.
Details
- Author
- birdsmith
- Repository
- Birdsmith/Gauntlet-Incept-MCP
- GitHub stars
- 1
- Categories
- AI, Design, File Management, Database, Knowledge Base, Developer Tools, Infrastructure
Jump to
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Gauntlet InceptCommand (node, npx, python, etc.)npxArguments-
Argument 1
-y -
Argument 2
@highlight/mcp-server
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
-
Argument 1
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
1. Clone the repository
git clone https://github.com/yourusername/Gauntlet-Incept.git
2. Navigate to the project directory
cd Gauntlet-Incept
3. Install dependencies
npm install
4. Copy the example environment file and update it with your values
cp .env.example .env
5. Run the project
npm start
1. Build and start the containers
docker-compose up -d
2. Access the API at http://localhost:3000
3. Access the MCP server at http://localhost:3001
tag_question
Tag a question with subject, grade, standard, lesson, and difficulty. Endpoint: POST /api/question/tag
grade_question
Grade a tagged question against quality standards. Endpoint: POST /api/question/grade
generate_question
Generate a question based on tags or an example question. Endpoint: POST /api/question/generate
tag_article
Tag an article with subject, grade, standard, and lesson. Endpoint: POST /api/article/tag
grade_article
Grade a tagged article against quality standards. Endpoint: POST /api/article/grade
generate_article
Generate an article based on tags or an example article. Endpoint: POST /api/article/generate
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"gauntlet incept": {
"env": {},
"args": [
"-y",
"@highlight/mcp-server"
],
"command": "npx"
}
}
}
Linux
{
"env": [],
"args": [
"-y",
"@highlight/mcp-server"
],
"command": "npx"
}
Macos
{
"env": [],
"args": [
"-y",
"@highlight/mcp-server"
],
"command": "npx"
}
Windows
{
"env": [],
"args": [
"/c",
"npx",
"-y",
"@highlight/mcp-server"
],
"command": "cmd"
}
Gauntlet-Incept
A system for generating high-quality educational content tailored to students' knowledge levels and interests.
Project Description
This repository contains the code and resources for the Gauntlet-Incept project, which aims to build a system that generates high-quality educational content for K-8 students. The initial scope focuses on developing educational content in the form of articles and question banks for specific subject areas.
Documentation
- Project Overview - Detailed description of the project goals and requirements
- Implementation Checklist - Comprehensive checklist for project implementation
- Original Project Brief - Original project brief with detailed requirements
- MCP Server Guide - Guide for using the Model Context Protocol server with Claude Desktop
Project Structure
gauntlet-incept/
├── docs/ # Documentation files
├── src/ # Source code
│ ├── api/ # API routes
│ ├── models/ # Data models
│ ├── services/ # Business logic
│ ├── utils/ # Utility functions
│ ├── data/ # Data files
│ ├── tests/ # Test files
│ ├── index.js # Entry point for REST API
│ └── mcp-server.js # Model Context Protocol server
├── services/ # Microservices
│ ├── qti-service/ # QTI service for content storage
│ └── llm-service/ # LLM service for content generation
├── .env.example # Example environment variables
├── .gitignore # Git ignore file
├── package.json # Node.js package file
├── docker-compose.yml # Docker Compose configuration
├── Dockerfile # Docker configuration
└── README.md # This file
API Endpoints
The project implements six core API endpoints:
Question Endpoints
- POST /api/question/tag - Tag a question with subject, grade, standard, lesson, and difficulty
- POST /api/question/grade - Grade a tagged question against quality standards
- POST /api/question/generate - Generate a question based on tags or an example question
Article Endpoints
- POST /api/article/tag - Tag an article with subject, grade, standard, and lesson
- POST /api/article/grade - Grade a tagged article against quality standards
- POST /api/article/generate - Generate an article based on tags or an example article
Model Context Protocol (MCP) Server
In addition to the REST API, this project includes an MCP server that allows Claude Desktop to interact with the Gauntlet Incept system. This enables Claude to generate, tag, and grade educational content directly.
See the MCP Server Guide for details on how to set up and use the MCP server with Claude Desktop.
Getting Started
Prerequisites
- Git
- Node.js (v14 or higher)
- Access to the RDS PostgreSQL database (credentials provided by administrator)
- SSH key for database connection (if connecting through SSH tunnel)
- Docker and Docker Compose (optional, for containerized deployment)
Installation
1. Clone the repository
git clone https://github.com/yourusername/Gauntlet-Incept.git
2. Navigate to the project directory
cd Gauntlet-Incept
3. Install dependencies
npm install
4. Copy the example environment file and update it with your values
cp .env.example .env
5. Run the project
npm start
Running with Docker
1. Build and start the containers
docker-compose up -d
2. Access the API at http://localhost:3000
3. Access the MCP server at http://localhost:3001
Database Connection
This project connects to an Amazon RDS PostgreSQL instance with the following details:
- Host: alphacommoncrawl-core-reboot.cluster-caeuiwckzo1a.us-east-1.rds.amazonaws.com
- Port: 5432
- Database: core
- Username: postgres
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
