Linkedin Browser MCP Server

🚀 LinkedIn Browser MCP Server

A FastMCP-based server for LinkedIn automation and data extraction using browser automation. This server provides a set of tools for programmatic interaction with LinkedIn while respecting its terms of service and rate limits.

🚀 Quick Start

This server is designed to automate interactions and extract data from LinkedIn. It offers a range of tools to interact with LinkedIn in a secure and efficient way.

✨ Features

Security Authentication

• Environment-based credential management.
• Session persistence with encrypted cookie storage.
• Protection against rate limits.
• Automatic session recovery.

Profile Operations

• View and extract profile information.
• Search for profiles based on keywords.
• Browse LinkedIn feeds.
• Access profile features.

Post Interaction

• Like posts.
• Comment on posts.
• Read post content and engagement metrics.

📦 Installation

Prerequisites

• Python 3.8+
• Playwright
• FastMCP library
• LinkedIn account

Steps

1. Clone the repository:

git clone [repository_url]
cd mcp-linkedin-server

2. Create and activate a virtual environment:

python -m venv env
source env/bin/activate  # On Windows: env\Scripts\activate

3. Install dependencies:

pip install -r requirements.txt
playwright install chromium

4. Set up environment variables: Create a .env file in the root directory with the following content:

LINKEDIN_USERNAME=your_email@example.com
LINKEDIN_PASSWORD=your_password
COOKIE_ENCRYPTION_KEY=your_encryption_key  # Optional: will be auto-generated if not provided

💻 Usage Examples

Basic Usage

1. Start the MCP server:

python linkedin_browser_mcp.py

2. Available tools:

• login_linkedin_secure: Securely log in using environment credentials.
• browse_linkedin_feed: Browse and extract posts from the feed.
• search_linkedin_profiles: Search for profiles that meet the criteria.
• view_linkedin_profile: View and extract data from a specific profile.
• interact_with_linkedin_post: Like, comment on, or read a post.

Code Example

from fastmcp import FastMCP

# Initialize the client
client = FastMCP.connect("http://localhost:8000")

# Log in
result = await client.login_linkedin_secure()
print(result)

# Search for profiles
profiles = await client.search_linkedin_profiles(
    query="software engineer",
    count=5
)
print(profiles)

# View a profile
profile_data = await client.view_linkedin_profile(
    profile_url="https://www.linkedin.com/in/username"
)
print(profile_data)

🔧 Technical Details

Security Features

• Encrypted cookie storage.
• Protection against rate limits.
• Secure credential management.
• Session persistence.
• Security measures for browser automation.

Best Practices

Rate Limit Prevention

The server implements features to prevent excessive requests:

• A maximum of 5 login attempts per hour.
• Automatic session reuse.
• Cookie persistence to reduce the need for logins.

Error Handling

Comprehensive error handling for:

• Network issues.
• Authentication failures.
• LinkedIn security challenges.
• Invalid URLs or parameters.

Session Management

• Automatic cookie encryption.
• Session persistence.
• Secure storage practices.

🤝 Contribution Guidelines

1. Fork the repository.
2. Create a feature branch.
3. Commit your changes.
4. Push to the branch.
5. Create a pull request.

📄 License

MIT

⚠️ Disclaimer

This tool is for educational purposes only. When using this software, ensure compliance with LinkedIn's terms of service and rate limit guidelines.