NvkAnirudh YT to LinkedIn MCP Server

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

• YouTube Transcript Extraction: Extract transcripts from YouTube videos using video URLs
• Transcript 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

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

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 with 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 at http://localhost:8000/docs

1. Build the Docker image:

   docker build -t yt-to-linkedin-mcp .

2. Run the container:

   docker run -p 8000:8000 --env-file .env yt-to-linkedin-mcp

1. Ensure you have the Smithery CLI installed and configured.

2. Deploy to Smithery:

   smithery deploy

Endpoint: /api/v1/transcript
Method: POST
Description: Extract transcript from a YouTube video

Request Body:

{
  "youtube_url": "https://www.youtube.com/watch?v=VIDEO_ID",
  "language": "en",
  "youtube_api_key": "your_youtube_api_key"  // Optional, provide your own YouTube API key
}

Response:

{
  "video_id": "VIDEO_ID",
  "video_title": "Video Title",
  "transcript": "Full transcript text...",
  "language": "en",
  "duration_seconds": 600,
  "channel_name": "Channel Name",
  "error": null
}

Endpoint: /api/v1/summarize
Method: POST
Description: Generate a summary from a video transcript

Request Body:

{
  "transcript": "Video transcript text...",
  "video_title": "Video Title",
  "tone": "professional",
  "audience": "general",
  "max_length": 250,
  "min_length": 150,
  "openai_api_key": "your_openai_api_key"  // Optional, provide your own OpenAI API key
}

Response:

{
  "summary": "Generated summary text...",
  "word_count": 200,
  "key_points": [
    "Key point 1",
    "Key point 2",
    "Key point 3"
  ]
}

Endpoint: /api/v1/generate-post
Method: POST
Description: Generate a LinkedIn post from a video summary

Request Body:

{
  "summary": "Video summary text...",
  "video_title": "Video Title",
  "video_url": "https://www.youtube.com/watch?v=VIDEO_ID",
  "speaker_name": "Speaker Name",
  "hashtags": ["ai", "machinelearning"],
  "tone": "professional",
  "voice": "first_person",
  "audience": "technical",
  "include_call_to_action": true,
  "max_length": 1200,
  "openai_api_key": "your_openai_api_key"  // Optional, provide your own OpenAI API key
}

Response:

{
  "post_content": "Generated LinkedIn post content...",
  "character_count": 800,
  "estimated_read_time": "About 1 minute",
  "hashtags_used": ["#ai", "#machinelearning"]
}

Endpoint: /api/v1/output
Method: POST
Description: Format the LinkedIn post for output

Request Body:

{
  "post_content": "LinkedIn post content...",
  "format": "json"
}

Response:

{
  "content": {
    "post_content": "LinkedIn post content...",
    "character_count": 800
  },
  "format": "json"
}

Note: While environment variables for API keys are optional (as they can be provided in each request), it's recommended to set them for local development and testing. When deploying to Smithery, users will need to provide their own API keys in the requests.

MIT