Jobspy MCP Server

🚀 JobSpy MCP Server

A Model Context Protocol (MCP) server that enables AI assistants (such as Claude) to search for job listings on multiple job recruitment platforms using the JobSpy tool.

🚀 Quick Start

The JobSpy MCP Server allows AI assistants to search for jobs across various platforms. Here's a quick overview of how to get started.

✨ Features

• Search for jobs on multiple platforms such as Indeed, LinkedIn, and Glassdoor.
• Filter job information based on keywords, location, and time.
• Return structured data for AI processing.
• Support output results in JSON and CSV formats.

📦 Installation

Prerequisites

• Node.js 16 or higher.
• Python 3.6 or higher.
• The JobSpy tool installed.

Installation Steps

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

# Install dependencies
npm install

# Set up the JobSpy environment
pip install jobspy

📚 Documentation

Configuration

The server automatically locates the JobSpy script and can be configured via the following environment variables:

Configuration Methods

1. Using the Command Line

   export JOBSPY_DOCKER_IMAGE=jobspy-mcp-server:latest
   export JOBSPY_ACCESS_TOKEN=your_access_token
   

2. Creating a .env File

   Create a .env file in the project root directory and add the following content:

   JOBSPY_DOCKER_IMAGE=jobspy-mcp-server:latest
   JOBSPY_ACCESS_TOKEN=your_access_token
   

Usage

Starting the Server

npm start

Integrating with Claude Desktop

Add the following content to the configuration file to support integration with Claude:

{
  "claude": {
    "enabled": true,
    "apiKey": "your_claude_api_key"
  }
}

SSE Transmission Support

The server provides real-time streaming processing. Here's an example code for connection:

const eventSource = new EventSource('http://localhost:9423/sse');

eventSource.addEventListener('message', function(e) {
    console.log('Data:', e.data);
});

API Documentation

Search for Jobs

curl -X POST "http://localhost:9423/api" \
  -H "Content-Type: application/json" \
  -d '{
    "method": "search_jobs",
    "params": {
      "search_term": "Software Engineer",
      "location": "San Francisco, California",
      "site_names": "indeed,linkedin",
      "results_wanted": 10,
      "format": "json"
    }
  }'

Available Tools: search_jobs

Example Usage

I need to find senior software engineer positions in Boston posted within the last 24 hours.

Docker Support

Building the Image

docker build -t jobspy-mcp-server .

Running the Container

docker run -p 9423:9423 jobspy-mcp-server

Development Environment

Running in Development Mode

npm run dev

Running Tests

npm test