LinkedIn Post Generator

GitHub
Integrates with
YouTube

LinkedIn Post Generator

smithery badge

A Model Context Protocol (MCP) server that automates generating professional LinkedIn post drafts from YouTube videos. This tool streamlines content repurposing by extracting transcripts from YouTube videos, summarizing the content, and generating engaging LinkedIn posts tailored to your preferences.

Table of Contents

Features

  • YouTube Transcript Extraction: Automatically extract transcripts from any YouTube video
  • Content Summarization: Generate concise summaries with customizable tone and target audience
  • LinkedIn Post Generation: Create professional LinkedIn posts with customizable style and tone
  • All-in-One Workflow: Go from YouTube URL to LinkedIn post in a single operation
  • Customization Options: Adjust tone, audience, word count, and more to match your personal brand
  • MCP Integration: Works seamlessly with AI assistants that support the Model Context Protocol

Installation

Local Development

  1. Clone the repository:

    git clone https://github.com/NvkAnirudh/LinkedIn-Post-Generator.git
cd LinkedIn-Post-Generator

  2. Install dependencies:

    npm install

  3. Create a .env file based on the example:

    cp .env.example .env

  4. Add your API keys to the .env file:

    OPENAI_API_KEY=your_openai_api_key
YOUTUBE_API_KEY=your_youtube_api_key

  5. Run the server:

    npm run dev

  6. Test with MCP Inspector:

    npm run inspect

Using with Claude Desktop

This MCP server is designed to work with Claude Desktop and other AI assistants that support the Model Context Protocol. To use it with Claude Desktop:

  1. Configure Claude Desktop by editing the configuration file at ~/Library/Application Support/Claude/claude_desktop_config.json (Mac) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

    {
  "mcpServers": {
    "linkedin-post-generator": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli@latest",
        "run",
        "@NvkAnirudh/linkedin-post-generator",
        "--key",
        "YOUR_SMITHERY_API_KEY",
        "--config",
        "{\"OPENAI_API_KEY\":\"YOUR_OPENAI_API_KEY\",\"YOUTUBE_API_KEY\":\"YOUR_YOUTUBE_API_KEY\"}",
        "--transport",
        "stdio"
      ]
    }
  }
}

    Replace:

    • YOUR_SMITHERY_API_KEY with your Smithery API key
    • YOUR_OPENAI_API_KEY with your OpenAI API key
    • YOUR_YOUTUBE_API_KEY with your YouTube API key (optional)

  2. Restart Claude Desktop

  3. In Claude Desktop, you can now access the LinkedIn Post Generator tools without needing to set API keys again

Configuration

The application requires API keys to function properly:

  1. OpenAI API Key (required): Used for content summarization and post generation
  2. YouTube API Key (optional): Enhances YouTube metadata retrieval

You can provide these keys in three ways:

1. Via Claude Desktop Configuration (Recommended)

When using with Claude Desktop and Smithery, the best approach is to include your API keys in the Claude Desktop configuration file as shown in the Using with Claude Desktop section. This way, the keys are automatically passed to the MCP server, and you don't need to set them again.

2. As Environment Variables

When running locally, you can set API keys as environment variables in a .env file:

OPENAI_API_KEY=your_openai_api_key
YOUTUBE_API_KEY=your_youtube_api_key

3. Using the Set API Keys Tool

If you haven't provided API keys through the configuration or environment variables, you can set them directly through the MCP interface using the set_api_keys tool.

Usage

Available Tools

Set API Keys
  • Tool: set_api_keys
  • Purpose: Configure your API keys
  • Parameters:
    • openaiApiKey: Your OpenAI API key (required)
    • youtubeApiKey: Your YouTube API key (optional)
Check API Keys
  • Tool: check_api_keys
  • Purpose: Verify your API key configuration status
Extract Transcript
  • Tool: extract_transcript
  • Purpose: Get the transcript from a YouTube video
  • Parameters:
    • youtubeUrl: URL of the YouTube video
Summarize Transcript
  • Tool: summarize_transcript
  • Purpose: Create a concise summary of the video content
  • Parameters:
    • transcript: The video transcript text
    • tone: Educational, inspirational, professional, or conversational
    • audience: General, technical, business, or academic
    • wordCount: Approximate word count for the summary (100-300)
Generate LinkedIn Post
  • Tool: generate_linkedin_post
  • Purpose: Create a LinkedIn post from a summary
  • Parameters:
    • summary: Summary of the video content
    • videoTitle: Title of the YouTube video
    • speakerName: Name of the speaker (optional)
    • hashtags: Relevant hashtags (optional)
    • tone: First-person, third-person, or thought-leader
    • includeCallToAction: Whether to include a call to action
All-in-One: YouTube to LinkedIn Post
  • Tool: youtube_to_linkedin_post
  • Purpose: Complete workflow from YouTube URL to LinkedIn post
  • Parameters:
    • youtubeUrl: YouTube video URL
    • tone: Desired tone for the post
    • Plus additional customization options

Workflow Example

  1. Set your API keys using the set_api_keys tool
  2. Use the youtube_to_linkedin_post tool with a YouTube URL
  3. Receive a complete LinkedIn post draft ready to publish

Deployment

This server is deployed on Smithery, a platform for hosting and sharing MCP servers. The deployment configuration is defined in the smithery.yaml file.

To deploy your own instance:

  1. Create an account on Smithery
  2. Install the Smithery CLI: 
    npm install -g @smithery/cli
  3. Deploy the server: 
    smithery deploy

Contributing

Contributions are welcome and appreciated! Here's how you can contribute to the LinkedIn Post Generator:

Reporting Issues

  • Use the GitHub issue tracker to report bugs or suggest features
  • Please provide detailed information about the issue, including steps to reproduce, expected behavior, and actual behavior
  • Include your environment details (OS, Node.js version, etc.) when reporting bugs

Pull Requests

  1. Fork the repository
  2. Create a new branch (git checkout -b feature/your-feature-name)
  3. Make your changes
  4. Run tests to ensure your changes don't break existing functionality
  5. Commit your changes (git commit -m 'Add some feature')
  6. Push to the branch (git push origin feature/your-feature-name)
  7. Open a Pull Request

Development Guidelines

  • Follow the existing code style and conventions
  • Write clear, commented code
  • Include tests for new features
  • Update documentation to reflect your changes

Feature Suggestions

If you have ideas for new features or improvements:

  1. Check existing issues to see if your suggestion has already been proposed
  2. If not, open a new issue with the label 'enhancement'
  3. Clearly describe the feature and its potential benefits

Documentation

Improvements to documentation are always welcome:

  • Fix typos or clarify existing documentation
  • Add examples or use cases
  • Improve the structure or organization of the documentation

By contributing to this project, you agree that your contributions will be licensed under the project's MIT License.

License

MIT