Linkedin Jobs MCP Server

🚀 LinkedIn Jobs MCP Server

A Model Context Protocol (MCP) server for searching and retrieving LinkedIn job postings via the RapidAPI's LinkedIn Data API.

🚀 Quick Start

The LinkedIn Jobs MCP Server is a powerful tool that enables you to interact with LinkedIn job postings using the Model Context Protocol (MCP). This server allows Claude, an AI model, to search and retrieve job - related information, expanding its capabilities beyond the training data.

✨ Features

• Search for LinkedIn job postings using keywords.
• Filter jobs by location.
• Get detailed information about specific job postings.
• Location search functionality to find LinkedIn location IDs by keyword.

📦 Installation

Prerequisites

• Python 3.8+
• A RapidAPI key with access to the LinkedIn Data API
• Required Python packages (see requirements.txt)

Steps

1. Clone this repository:

git clone https://github.com/yourusername/linkedin-jobs-mcp.git
cd linkedin-jobs-mcp

2. Install the required packages:

pip install -r requirements.txt

3. Create a .env file in the project root directory and add your RapidAPI key:

RAPIDAPI_KEY=your_rapidapi_key_here

💻 Usage Examples

Basic Usage

Running the MCP Server

python main.py

This will start the MCP server using the stdio transport, suitable for integration with Claude via the Claude Desktop application.

Configuring Claude Desktop

To use this MCP server with Claude Desktop, add the following configuration to claude_desktop_config.json:

{
    "mcpServers": {
        "mcp-linkedin": {
            "command": "/path/to/python",
            "args": [
                "--directory",
                "/path/to/linkedin-jobs-mcp",
                "run",
                "main.py"
            ]
        }
    }
}

Example configuration:

{
    "mcpServers": {
        "documentation": {
            "command": "/Users/Rom/.local/bin/uv",
            "args": [
            "--directory",
            "/Users/Rom/Documents/personal_projects/documentation",
            "run",
            "main.py"
            ]
        }
    }
}

Advanced Usage

Available Tools

The MCP server provides the following tools:

1. search_jobs(keywords, limit = 10, location = 'Israel', format_output = True) - Search for jobs matching the keywords in the specified location.
2. get_job_details(job_id) - Get detailed information about a specific job posting.
3. search_locations(keyword) - Search for LinkedIn location IDs by keyword.

Example Interaction with Claude

Once your MCP server is configured via Claude Desktop, you can interact with it as follows:

Find programming - related jobs on LinkedIn.

Claude's response:

{
    "jobs": [
        {
            "title": "Senior Software Engineer",
            "company": "Tech Corp",
            "location": "Palo Alto, California, USA",
            "salary": "$120,000 - $150,000",
            "description": "We are looking for an experienced software engineer to join our team..."
        },
        {
            "title": "Front - End Developer",
            "company": "Web Solutions Inc.",
            "location": "London, UK",
            "salary": "£60,000 - £80,000",
            "description": "We are looking for a skilled front - end developer to help us build..."
        },
        // More jobs...
    ]
}

📚 Documentation

What is MCP?

The Model Context Protocol (MCP) is a framework developed by Anthropic that allows AI models like Claude to interact with external tools and APIs. MCP enables Claude to execute code, access databases, retrieve information from the internet, etc., significantly expanding its capabilities beyond the training data.

MCP works by defining a set of tools that can be invoked by Claude through a standardized protocol. When Claude needs information that requires external access, it can call these tools, which perform the necessary operations and return the results to Claude. This allows Claude to provide more accurate, timely, and context - relevant responses.

For more information about MCP, refer to Anthropic's announcement.

Credits

• Framework: Anthropic's MCP
• Data API: RapidAPI

📄 License

This project is licensed under the MIT License.

Contribution

Contributions are welcome! Please check CONTRIBUTING.md for how to contribute.