Google Jobs MCP Server

A Model Context Protocol (MCP) server implementation that provides Google Jobs search capabilities via SerpAPI integration. Features multi-language support, flexible search parameters, and smart error handling.

https://github.com/user-attachments/assets/8f6739e1-7db7-4171-88b4-59c6290a4c72

✨ Features

🌍 Multi-Language Support

Full localization support for English, Chinese, Japanese and Korean with automatic language detection and fallback.

🔍 Flexible Search Options

Comprehensive search parameters including:

• Job title and keywords
• Location with radius filtering
• Employment type (full-time, part-time, etc.)
• Salary range filters
• Post date filtering
• Results sorting

💡 Smart Error Handling

• Comprehensive input validation
• Helpful error messages and suggestions
• Automatic search refinement suggestions
• Rate limit handling

📊 Rich Job Details

• Detailed job information formatting
• Company benefits and highlights
• Salary information when available
• Direct application links
• Job posting timestamps

🔄 Advanced Features

• Pagination support
• Multiple sorting options
• Geographic radius search
• Employment type filtering

🔑 SERP API Setup Guide

Before getting started, you'll need to obtain a SERP API key:

1. Visit SERP API website and create an account

2. After registration, go to your Dashboard:

   • Locate the "API Key" section
   • Copy your API key
   • New users get 100 free API calls

3. API Usage Details:

   • Free tier: 100 searches per month
   • Paid plans start at $50/month for 5000 searches
   • Billing based on successful API calls
   • Multiple payment methods: Credit Card, PayPal, etc.

4. Usage Limits:

   • Request Rate: 2 requests/second
   • IP Restrictions: None
   • Concurrent Requests: 5
   • Response Cache Time: 1 hour

👩‍🔧 Solution for MCP Servers Connection Issues with NVM/NPM

Click to view my configuration solution 👉 https://github.com/modelcontextprotocol/servers/issues/76

🚀 Quick Start

1. Install dependencies:

npm install

2. Configure environment: Modify your claude_desktop_config.json with the following content (adjust paths according to your system):

{
  "google-jobs": {
    "command": "D:\\Program\\nvm\\node.exe",
    "args": ["D:\\github_repository\\path_to\\dist\\index.js"],
    "env": {
      "SERP_API_KEY": "your-api-key"
    }
  }
}

3. Build the server:

npm run build

4. Start the server:

npm start

Troubleshooting

1. API Key Issues:

• Verify key in configuration
• Check key status in SERP API dashboard
• Confirm key has remaining quota

2. Search Issues:

• Validate search parameters format
• Check network connectivity
• Verify country/language code support

📦 Installation

Installing via Smithery

To install Google Jobs for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @chanmeng666/google-jobs-server --client claude

Manual Installation

@chanmeng666/google-jobs-server

# Using npm
npm i @chanmeng666/google-jobs-server
# or
npm install @chanmeng666/google-jobs-server

# Using yarn
yarn add @chanmeng666/google-jobs-server

# Using pnpm
pnpm add @chanmeng666/google-jobs-server

Running evals

The evals package loads an mcp client that then runs the index.ts file, so there is no need to rebuild between tests. You can load environment variables by prefixing the npx command. Full documentation can be found here.

OPENAI_API_KEY=your-key  npx mcp-eval src/evals/evals.ts src/index.ts

💻 Tech Stack

📖 API Documentation

The server implements the Model Context Protocol and exposes a job search tool with the following parameters:

• query: Search query string (required)
• location: Job location (optional)
• posted_age: Post date filter (optional)
• employment_type: Job type filter (optional)
• salary: Salary range filter (optional)
• radius: Geographic search radius (optional)
• hl: Language code (optional)
• page: Pagination number (optional)
• sort_by: Sort order (optional)

🔧 Development

# Run in development mode
npm run dev

# Run type checking
npm run typecheck

# Build for production
npm run build

📝 License

This project is MIT licensed.

🙋‍♀ Author

Created and maintained by Chan Meng.