JobSpy MCP Server

A Model Context Protocol (MCP) server that enables AI assistants like Claude to search for jobs across multiple job listing platforms using the JobSpy tool.

Features

• Search for jobs across multiple platforms (Indeed, LinkedIn, Glassdoor, etc.)
• Filter by search terms, location, time frames, and more
• Get structured job data that AI models can easily process
• Format results as JSON or CSV
• Multiple transport options: stdio for Claude integration, SSE for web clients

Prerequisites

• Node.js 16+
• Python 3.6+
• The JobSpy tool installed and available

Installation

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

# Install dependencies
npm install

# Make sure the JobSpy tool is properly set up
cd ../jobSpy
pip install -r requirements.txt
chmod +x run.sh

Configuration

The server will automatically try to locate the JobSpy script in standard locations:

• ../jobSpy/run.sh (relative to the server directory)
• ./run.sh (in the current directory)
• /app/run.sh (for Docker environments)

Environment Variables

You can configure the server using the following environment variables:

Setting Up Configuration

You can set these configuration values in multiple ways:

1. Using environment variables directly

export JOBSPY_DOCKER_IMAGE=jobspy
export JOBSPY_HOST='0.0.0.0'
export JOBSPY_PORT=9423
export ENABLE_SSE=1

2. Using a .env file

Create a .env file in the root directory with your configuration:

JOBSPY_DOCKER_IMAGE=jobspy
JOBSPY_HOST='0.0.0.0'
JOBSPY_PORT=9423
ENABLE_SSE=1

Usage

Starting the server

npm start

Connecting with Claude Desktop

Add the following to your Claude Desktop config file (typically at ~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "jobspy": {
      "command": "node",
      "args": ["/path/to/jobspy-mcp-server/src/index.js"],
      "env": {
        "ENABLE_SSE": 0
      }
    }
  }
}

Using with Web Clients (SSE Transport)

The server exposes HTTP endpoints that allow web applications to interact with the JobSpy MCP server:

• Connect for updates: GET /mcp/connect

  • Establishes a Server-Sent Events (SSE) connection for real-time updates
  • Returns progress updates and job search results

• Send requests: POST /mcp/request

  • Accepts tool invocation requests in MCP format
  • Returns tool responses

Example JavaScript client for browser:

// Connect to SSE endpoint
const eventSource = new EventSource('http://localhost:9423/mcp/connect');

// Listen for updates
eventSource.onmessage = function(event) {
  const data = JSON.parse(event.data);
  console.log('Received update:', data);
  
  // Handle progress updates
  if (data.type === 'progress') {
    updateProgressBar(data.progress);
  }
};

// Send a search request
async function searchJobs() {
  const response = await fetch('http://localhost:9423/mcp/request', {
    method: 'POST',
    headers: {
      'Content-Type': 'application/json'
    },
    body: JSON.stringify({
      tool: 'search_jobs',
      params: {
        search_term: 'software engineer',
        location: 'San Francisco, CA',
        site_names: 'indeed,linkedin'
      }
    })
  });
  
  return await response.jso

... [View full README on GitHub](https://github.com/borgius/jobspy-mcp-server#readme)