LinkedIn Post Generator

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
• Installation
  • Local Development
  • Using with Claude Desktop
• Configuration
• Usage
  • Available Tools
  • Workflow Example
• Deployment
• License

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": [