Skip to main content
Glama

πŸŽ“ MCP Content Curation Server

Node.js TypeScript OpenAI License

A Model Context Protocol (MCP) server for intelligent course content curation powered by GPT-4. This server provides AI-driven tools to categorize, tag, and improve educational content.

✨ Features

  • πŸ—‚οΈ Smart Categorization: AI-powered category suggestions for course content

  • 🏷️ Intelligent Tagging: Context-aware tag recommendations using GPT-4

  • ✨ Content Optimization: Improve titles and descriptions following best practices

  • πŸ”Œ MCP Integration: Seamless integration with Claude Desktop and other MCP clients

Related MCP server: OpenEdu MCP Server

πŸš€ Quick Start

Prerequisites

  • Node.js 18+

  • OpenAI API key

Installation

  1. Clone the repository

    git clone https://github.com/yourusername/mcp-content-curation-server.git
    cd mcp-content-curation-server
  2. Install dependencies

    npm install
  3. Configure environment

    cp .env.example .env
    # Edit .env and add your OpenAI API key
  4. Run the server

    # Development mode
    npm run dev
    
    # Production mode
    npm run build
    npm start

πŸ”§ OpenAI Setup

  1. Get your API key from OpenAI Platform

  2. Add it to your .env file:

    OPENAI_API_KEY=sk-your-actual-api-key-here

πŸ–₯️ Claude Desktop Integration

Update your claude_desktop_config.json:

Development Mode:

{
  "mcpServers": {
    "content-curation": {
      "command": "npx",
      "args": ["tsx", "/path/to/your/project/src/server.ts"],
      "cwd": "/path/to/your/project",
      "env": {
        "NODE_ENV": "development"
      }
    }
  }
}

Production Mode:

{
  "mcpServers": {
    "content-curation": {
      "command": "node",
      "args": ["/path/to/your/project/dist/server.js"],
      "cwd": "/path/to/your/project",
      "env": {
        "NODE_ENV": "production"
      }
    }
  }
}

πŸ› οΈ Available Tools

1. suggest_category

Suggests the most appropriate category for course content.

Input:

{
  "title": "Python for Data Science",
  "description": "Learn data analysis with pandas and matplotlib"
}

2. suggest_tags

Recommends relevant tags based on course content.

Input:

{
  "title": "Digital Marketing Fundamentals",
  "description": "Master SEO, Google Ads, and social media marketing"
}

3. improve_content

Optimizes titles and descriptions following educational best practices.

Input:

{
  "title": "JavaScript Basics",
  "description": "Learn programming fundamentals"
}

πŸ“Š Data Structure

The server includes:

  • 5 main categories: Technology, Business, Design, Marketing, Analytics

  • 18 contextual tags: Organized by subject area

  • 10 sample courses: For similarity analysis and training

πŸ’‘ Usage Examples

Categorization

Suggest a category for: "Advanced React Hooks" - "Custom hooks and performance optimization in React"

Tagging

What tags would you recommend for: "Machine Learning with Python"?

Content Improvement

Improve this content:
Title: "Excel Basics"
Description: "Learn spreadsheets"

πŸ› οΈ Development

Available Scripts

  • npm run dev - Start development server

  • npm run build - Compile TypeScript

  • npm start - Run production server

  • npm run debug - Run diagnostics

Project Structure

src/
β”œβ”€β”€ server.ts              # Main MCP server
β”œβ”€β”€ services/
β”‚   β”œβ”€β”€ ai.service.ts       # OpenAI GPT-4 integration
β”‚   └── curation.service.ts # Curation logic
β”œβ”€β”€ data/
β”‚   └── mock-data.ts        # Categories, tags, and sample data
└── types.ts               # TypeScript definitions

Available Tools

3 tools
improve_contentC

Melhora tΓ­tulo e descriΓ§Γ£o de um curso seguindo boas prΓ‘ticas

Inputs: title (required), description (required).

suggest_categoryC

Sugere categoria mais apropriada para um curso usando IA

Inputs: title (required), description (required).

suggest_tagsB

Sugere tags relevantes para um curso usando IA

Inputs: title (required), description (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.2/5.0

    Scored across 3 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: improve_content focuses on enhancing title and description, suggest_category recommends a category, and suggest_tags suggests tags. There is no overlap in functionality, making it easy for an agent to select the correct tool without confusion.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern (improve_content, suggest_category, suggest_tags) with the same verb style ('improve' and 'suggest'). This predictability aids in understanding and usage without deviation.

    Tool Count3/5

    With only 3 tools, the server feels thin for a content curation domain, as it lacks operations like creating, updating, or deleting content. While the tools are focused, the scope is limited, potentially requiring workarounds for full curation workflows.

    Completeness2/5

    The toolset is severely incomplete for content curation, missing core CRUD operations (e.g., create_content, update_content, delete_content) and other essential functions like listing or searching content. This will likely cause agent failures in handling comprehensive curation tasks.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers