LinkedIn Model Context Protocol (MCP) Server

A powerful Model Context Protocol server for LinkedIn interactions that enables AI assistants to search for jobs, generate resumes and cover letters, and manage job applications programmatically.

Features

• Authentication: Secure LinkedIn authentication with session management
• Profile Management: Access and update LinkedIn profile information
• Job Search: Search for jobs with flexible filtering options
• Resume Generation: Create customized resumes from LinkedIn profiles
• Cover Letter Generation: Generate tailored cover letters for specific job applications
• Job Applications: Submit and track job applications

Architecture

This project implements the Model Context Protocol (MCP) specification, allowing AI assistants to interact with LinkedIn through standardized JSON-RPC style requests and responses.

Components:

• MCP Handler: Routes requests to appropriate service handlers
• API Modules: Specialized modules for LinkedIn interactions (auth, job search, profile, etc.)
• Core Protocol: Defines request/response structures and data models
• Utilities: Configuration management and helper functions

Installation

# Clone the repository
git clone https://github.com/yourusername/linkedin-mcp.git
cd linkedin-mcp

# Create and activate a virtual environment
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

Configuration

Create a .env file in the project root with the following variables:

# LinkedIn Credentials
LINKEDIN_USERNAME=your_email@example.com
LINKEDIN_PASSWORD=your_password

# API Settings
OPENAI_API_KEY=your_openai_api_key
SESSION_DIR=sessions
DATA_DIR=data

Usage

Starting the Server

python server.py

Example MCP Requests

Authentication

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "linkedin.login",
  "params": {
    "username": "user@example.com",
    "password": "password123"
  }
}

Searching for Jobs

{
  "jsonrpc": "2.0",
  "id": 2,
  "method": "linkedin.searchJobs",
  "params": {
    "filter": {
      "keywords": "software engineer",
      "location": "New York, NY",
      "distance": 25
    },
    "page": 1,
    "count": 20
  }
}

Generating a Resume

{
  "jsonrpc": "2.0",
  "id": 3,
  "method": "linkedin.generateResume",
  "params": {
    "profileId": "user123",
    "template": "standard",
    "format": "pdf"
  }
}

Available Methods

Development

Project Structure

linkedin-mcp/
├── README.md
├── requirements.txt
├── server.py
├── data/
│   ├── applications/
│   ├── companies/
│   ├── cover_letters/
│   ├── jobs/
│   ├── profiles/
│   └── resumes/
├── linkedin_mcp/
│   ├── api/
│   │   ├── auth.py
│   │   ├── cover_letter_generator.py
│   │   ├── job_application.py
│   │   ├── job_search.py
│   │   ├── profile.py
│   │   └── resume_generator.py
│   ├── core/
│   │   ├── mcp_handler.py
│   │   └── protocol.py
│   └── utils/
│       └── config.py
├── sessions/
└── templates/
    ├── cover_letter/
    │   └── standard.html
    └── resume/
        └── standard.html

Running Tests

pytest

License

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

Acknowledgments

• LinkedIn API documentation
• Model Context Protocol specification

Shared threads will appear here, showcasing real-world applications and insights from the community. Check back soon for updates!