Abhirajsinghchandrawat/linkedin-mcp-server

LinkedIn Automation MCP Server

A complete end-to-end Model Context Protocol (MCP) server for LinkedIn automation tasks. This server provides tools for automating various LinkedIn activities including login, search, connection requests, messaging, posting, and data extraction.

Features

• Authentication: Secure LinkedIn login with session management
• People Search: Search for LinkedIn users with various filters
• Connection Management: Send connection requests with custom messages
• Messaging: Send direct messages to connections
• Content Creation: Create and publish LinkedIn posts
• Engagement: Like and comment on posts
• Data Extraction: Extract profile and company information
• Rate Limiting: Built-in rate limiting to avoid detection
• Error Handling: Comprehensive error handling and logging

Installation

Prerequisites

• Python 3.8 or higher
• Chrome browser installed
• LinkedIn account

Setup

1. Clone or download the project files

2. Install dependencies:

   pip install -r requirements.txt
   

3. Install Chrome WebDriver (automatically handled by webdriver-manager)

Usage

Starting the Server

python linkedin_mcp_server.py

Available Tools

1. LinkedIn Login

{
  "name": "linkedin_login",
  "arguments": {
    "email": "your-email@example.com",
    "password": "your-password",
    "headless": false
  }
}

2. Search People

{
  "name": "linkedin_search_people",
  "arguments": {
    "keywords": "software engineer",
    "location": "San Francisco",
    "company": "Google",
    "max_results": 50
  }
}

3. Send Connection Request

{
  "name": "linkedin_connect_with_person",
  "arguments": {
    "profile_url": "https://www.linkedin.com/in/username/",
    "message": "Hi, I'd like to connect!",
    "note": "I saw your profile and thought we could connect."
  }
}

4. Send Message

{
  "name": "linkedin_send_message",
  "arguments": {
    "profile_url": "https://www.linkedin.com/in/username/",
    "message": "Hello! How are you?",
    "subject": "Greeting"
  }
}

5. Create Post

{
  "name": "linkedin_post_content",
  "arguments": {
    "content": "Excited to share my latest project!",
    "visibility": "public",
    "hashtags": ["automation", "linkedin", "networking"]
  }
}

6. Like Post

{
  "name": "linkedin_like_post",
  "arguments": {
    "post_url": "https://www.linkedin.com/posts/activity-123"
  }
}

7. Comment on Post

{
  "name": "linkedin_comment_on_post",
  "arguments": {
    "post_url": "https://www.linkedin.com/posts/activity-123",
    "comment": "Great post! Thanks for sharing."
  }
}

8. Extract Profile Information

{
  "name": "linkedin_get_profile_info",
  "arguments": {
    "profile_url": "https://www.linkedin.com/in/username/"
  }
}

9. Extract Company Information

{
  "name": "linkedin_scrape_company_info",
  "arguments": {
    "company_url": "https://www.linkedin.com/company/company-name/"
  }
}

10. Logout

{
  "name": "linkedin_logout",
  "arguments": {}
}

Configuration

The server uses config.json for configuration settings:

• Browser Settings: Headless mode, user agent, window size
• Automation Settings: Delays, retries, rate limiting
• LinkedIn URLs: Various LinkedIn page URLs
• CSS Selectors: Element selectors for automation

Security and Best Practices

Rate Limiting

• Built-in rate limiting to avoid LinkedIn's detection
• Configurable delays between actions
• Maximum requests per minute setting

Session Management

• Secure login handling
• Automatic session cleanup on logout
• Browser instance management

Error Handling

• Comprehensive error catching and reporting
• Graceful failure handling
• Detailed logging for debugging

Troubleshooting

Common Issues

1. Login Failed

   • Check credentials
   • Ensure 2FA is disabled or handled
   • Try headless mode

2. Element Not Found

   • LinkedIn may have updated their UI
   • Check selectors in config.json
   • Add delays between actions

3. Rate Limiting

   • Reduce request frequency
   • Increase delays between actions
   • Use headless mode

4. Browser Issues

   • Update Chrome browser
   • Clear browser cache
   • Check ChromeDriver compatibility

Debug Mode

Enable debug logging by modifying the logging level in the code:

logging.basicConfig(level=logging.DEBUG)

Legal and Ethical Considerations

⚠️ Important: This tool is for educational and legitimate business purposes only.

• Respect LinkedIn's Terms of Service
• Don't spam or harass users
• Use reasonable delays between actions
• Don't exceed LinkedIn's rate limits
• Respect user privacy and consent

Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests if applicable
5. Submit a pull request

License

This project is licensed under the MIT License - see the LICENSE file for details.

Support

For issues and questions:

1. Check the troubleshooting section
2. Review the logs for error details
3. Create an issue with detailed information

Changelog

Version 1.0.0

• Initial release
• Complete LinkedIn automation functionality
• MCP server implementation
• Comprehensive tool set
• Configuration management