Skip to main content
Yanked

This release has been yanked by its maintainers, and will be ignored by installers, except when explicitly specified.
Reason given by maintainers: fix

JobSpy MCP Server

A modern MCP (Model Context Protocol) server that provides job scraping capabilities using the JobSpy library. Built with the latest FastMCP framework for seamless integration with Claude Desktop and other MCP clients.

🚀 Features

  • Multi-site job scraping: Search across 8 major job boards (LinkedIn, Indeed, Glassdoor, ZipRecruiter, Google Jobs, Bayt, Naukri, BDJobs)
  • Advanced filtering: Filter by job type, location, posting date, remote work, salary range, and more
  • Real-time progress: Get live updates during job searches with progress indicators
  • Rich formatting: Beautifully formatted job results with all relevant details
  • Modern MCP implementation: Built with FastMCP for 2025 MCP protocol compliance
  • Error handling: Robust error handling with informative messages
  • Comprehensive tools: Multiple tools for job searching, country/site information, and search tips

📦 Installation

Prerequisites

  • Python 3.10 or higher
  • uv (recommended) or pip

Quick Install

# Clone or download the project
cd jobspy-mcp-server

# Install with uv (recommended)
uv sync

# Or install with pip
pip install -e .

Install Dependencies Manually

pip install mcp>=1.1.0 python-jobspy>=1.1.82 pandas>=2.1.0 pydantic>=2.0.0

🔧 Usage

# Development mode with auto-reload
uv run mcp dev server.py

# Production mode
uv run mcp run server.py

# Direct execution
uv run python server.py

Run with Python

python server.py

Install in Claude Desktop

Add to your Claude Desktop configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "jobspy": {
      "command": "uv",
      "args": ["run", "python", "/full/path/to/jobspy-mcp-server/server.py"]
    }
  }
}

Alternative configuration:

{
  "mcpServers": {
    "jobspy": {
      "command": "python",
      "args": ["/full/path/to/jobspy-mcp-server/server.py"]
    }
  }
}

🛠️ Available Tools

1. scrape_jobs_tool

Search for jobs across multiple job boards with comprehensive filtering options.

Parameters:

  • search_term (required): Job keywords (e.g., "software engineer", "data scientist")
  • location: Job location (e.g., "San Francisco, CA", "Remote")
  • site_name: List of job boards to search (default: ["indeed", "linkedin", "zip_recruiter", "google"])
  • results_wanted: Number of results (1-1000, default: 15)
  • job_type: Employment type ("fulltime", "parttime", "internship", "contract")
  • is_remote: Filter remote jobs only (default: false)
  • hours_old: Filter by posting recency in hours
  • distance: Search radius in miles (1-100, default: 50)
  • easy_apply: Filter jobs with easy apply (default: false)
  • country_indeed: Country for Indeed/Glassdoor (default: "usa")
  • linkedin_fetch_description: Get full LinkedIn descriptions (slower, default: false)
  • offset: Pagination offset (default: 0)
  • verbose: Logging level (0-2, default: 1)

2. get_supported_countries

Get the complete list of supported countries for job searches.

3. get_supported_sites

Get detailed information about all supported job board sites.

4. get_job_search_tips

Get comprehensive tips and best practices for effective job searching.

💡 Example Queries

Ask Claude:

"Find me 25 remote Python developer jobs from Indeed and LinkedIn"

"Search for data scientist positions in San Francisco posted in the last 48 hours"

"Look for entry-level marketing jobs in New York with easy apply options"

"Show me all supported job sites and their descriptions"

"Give me tips for searching software engineering jobs effectively"

🌍 Supported Job Boards

  • LinkedIn: Professional networking platform (rate limited)
  • Indeed: Largest job search engine (most reliable)
  • Glassdoor: Jobs with company reviews and salaries
  • ZipRecruiter: Job matching for US/Canada
  • Google Jobs: Aggregated job listings
  • Bayt: Middle East job portal
  • Naukri: India's leading job portal
  • BDJobs: Bangladesh job portal

🌎 Supported Countries

The server supports 50+ countries including:

  • USA, Canada, UK, Australia
  • Germany, France, Spain, Italy
  • India, Singapore, Japan, South Korea
  • And many more...

Use get_supported_countries tool for the complete list.

🚨 Rate Limiting & Best Practices

  • LinkedIn: Most restrictive, use sparingly
  • Indeed: Most reliable, good for large searches
  • Start small: Begin with 10-15 results
  • Use filtering: Leverage job_type, hours_old, is_remote filters
  • Be specific: Use targeted search terms for better results

🔍 Advanced Search Examples

Remote Software Jobs

{
  "search_term": "software engineer",
  "location": "Remote", 
  "is_remote": true,
  "site_name": ["indeed", "zip_recruiter"],
  "results_wanted": 20
}

Recent Data Science Jobs

{
  "search_term": "data scientist",
  "location": "San Francisco, CA",
  "hours_old": 48,
  "site_name": ["linkedin", "glassdoor"],
  "linkedin_fetch_description": true
}

Entry Level Positions

{
  "search_term": "junior developer",
  "job_type": "fulltime",
  "easy_apply": true,
  "site_name": ["indeed", "zip_recruiter"],
  "results_wanted": 30
}

🧪 Testing

Run the test suite:

# With uv
uv run pytest

# With pip
pip install pytest
pytest

🤝 Contributing

  1. Fork the repository
  2. Create a feature branch
  3. Make your changes
  4. Add tests if applicable
  5. Submit a pull request

📄 License

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

🔧 Troubleshooting

Common Issues

"Module not found" errors

  • Ensure all dependencies are installed: uv sync or pip install -e .

"No results found"

  • Try broader search terms
  • Check different job boards
  • Verify location spelling

Rate limiting/blocking

  • Reduce results_wanted parameter
  • Use different job boards (avoid LinkedIn for large searches)
  • Add delays between searches

Claude Desktop not detecting tools

  • Verify configuration file path and JSON syntax
  • Restart Claude Desktop after configuration changes
  • Check server logs for errors

Getting Help

  1. Check the comprehensive get_job_search_tips tool
  2. Review the example queries above
  3. Start with small searches and expand gradually
  4. Use verbose logging (verbose=2) for debugging

🚀 Quick Start

  1. Install: uv sync
  2. Test: uv run mcp dev server.py
  3. Configure Claude Desktop with the server path
  4. Ask Claude: "Find me remote Python jobs using JobSpy"

Happy job hunting! 🎯

Metadata

Release files for jobspy-mcp-server 1.0.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for jobspy-mcp-server 1.0.0
File Size Uploaded Provenance
jobspy_mcp_server-1.0.0.tar.gz 22.4 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for jobspy-mcp-server 1.0.0
File Interpreter ABI Platform
jobspy_mcp_server-1.0.0-py3-none-any.whl Python 3 none any Details

Total release size: 33.7 kB

Release files / jobspy_mcp_server-1.0.0.tar.gz

Download URL jobspy_mcp_server-1.0.0.tar.gz
Size 22.4 kB
Tags Source
SHA-256 checksum
How to use checksums
715b1c3ce365d207f74b9bb0533cb96b2c2acca537212656910b13104f58b5e8
BLAKE2b-256 checksum
How to use checksums
8c63370358c2802186cf63d5ed091914abe0c0711c67515963f6bf0fc0fed279
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.13.5

Release files / jobspy_mcp_server-1.0.0-py3-none-any.whl

Download URL jobspy_mcp_server-1.0.0-py3-none-any.whl
Size 11.3 kB
Tags Python 3
SHA-256 checksum
How to use checksums
6add6111916939203940c3843f65bba596171069751f1e70488ae75118719363
BLAKE2b-256 checksum
How to use checksums
1c1ff283e4f0a55c9b569729aa0a8e1d3d66201ed00aba208bbdb8efe2bb4b16
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.13.5

Security for jobspy-mcp-server 1.0.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

1.0.0 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page