Nvkanirudh YT To LinkedIn MCP Server

🚀 YouTube to LinkedIn MCP Server

A Model Context Protocol (MCP) server that automates the generation of LinkedIn post drafts from YouTube videos. This server provides high-quality, editable content drafts based on YouTube video subtitles.

🚀 Quick Start

The YouTube to LinkedIn MCP Server is designed to streamline the process of creating LinkedIn post drafts from YouTube videos. It extracts subtitles, summarizes content, and generates professional LinkedIn posts with customizable tone and style.

✨ Features

• YouTube Subtitle Extraction: Extract subtitles from YouTube videos via video links.
• Subtitle Summarization: Generate concise summaries of video content using OpenAI GPT.
• LinkedIn Post Generation: Create professional LinkedIn post drafts with customizable tone and style.
• Modular API Design: Clean FastAPI implementation with well-defined endpoints.
• Containerized Deployment: Ready for deployment on Smithery.

📦 Installation

Prerequisites

• Python 3.8+
• Docker (for containerized deployment)
• OpenAI API key
• YouTube Data API key (optional but recommended for better metadata)

Local Development

1. Clone the repository:

   git clone <repository-url>
   cd yt-to-linkedin
   

2. Create a virtual environment and install dependencies:

   python -m venv venv
   source venv/bin/activate  # On Windows: venv\Scripts\activate
   pip install -r requirements.txt
   

3. Create a .env file in the project root directory and add your API keys:

   OPENAI_API_KEY=your_openai_api_key
   YOUTUBE_API_KEY=your_youtube_api_key
   

4. Run the application:

   uvicorn app.main:app --reload
   

5. Access the API documentation: http://localhost:8000/docs

Docker Deployment

1. Build the image:

   docker build -t yt-to-linkedin .
   

2. Run the container:

   docker run -p 8000:8000 --env OPENAI_API_KEY=your_key --env YOUTUBE_API_KEY=your_key yt-to-linkedin
   

💻 Usage Examples

Basic Usage

To extract subtitles from a YouTube video, send a POST request to the /api/v1/subtitles endpoint:

import requests

url = "http://localhost:8000/api/v1/subtitles"
data = {
    "video_id": "your_video_id"
}

response = requests.post(url, json=data)
print(response.json())

Advanced Usage

To generate a LinkedIn post, send a POST request to the /api/v1/post endpoint:

import requests

url = "http://localhost:8000/api/v1/post"
data = {
    "title": "Your Post Title",
    "content": "Your post content here...",
    "format": "markdown"
}

response = requests.post(url, json=data)
print(response.json())

📚 Documentation

API Endpoints

1. YouTube Subtitle Extraction

Endpoint: /api/v1/subtitles

Method: POST

Request Body:

{
  "video_id": "string"
}

Response:

{
  "subtitles": {
    "content": "string",
    "language": "string"
  }
}

2. LinkedIn Post Generation

Endpoint: /api/v1/post

Method: POST

Request Body:

{
  "title": "string",
  "content": "string",
  "format": "markdown" | "plain"
}

Response:

{
  "post": {
    "id": "string",
    "content": "string",
    "character_count": integer
  }
}

3. Output Formatting

Endpoint: /api/v1/output

Method: POST

Request Body:

{
  "post_content": "string",
  "format": "json"
}

Response:

{
  "content": {
    "post_content": "string",
    "character_count": integer
  },
  "format": "json"
}

Environment Variables

⚠️ Important Note

Although the API keys in environment variables are optional (as they can be provided in each request), it is recommended to set them during local development and testing. When deploying to Smithery, users need to provide their own API keys in requests.

📄 License

MIT