Best for
- Users who need quick access to job listings from major Chinese recruitment sites
- Developers who want to integrate natural language job search into AI assistants
- Those who prefer a zero-configuration, out-of-the-box setup
M
26FMRS · D
This project offers zero-config job search functionality, suitable for individuals and developers to quickly integrate into AI assistants, but relies on scraping, posing compliance and stability risks.
mcp-jobs is an MCP-based job aggregation service that fetches job listings from major Chinese recruitment websites like Liepin, Boss, Zhilian, and 51job. It offers a zero-configuration experience with no API keys or registration required. Start with a single command, search jobs, get details, and aggregate data from multiple platforms, with standardized output for easy AI processing.
Tools
search_jobs
Search for jobs by title, city, salary range, etc.
get_job_details
Get detailed information for a specific job, including requirements and salary.
Setup
Run npx -y mcp-jobs in a terminal to start the service, then add an MCP server in your AI client (e.g., Claude Desktop, Cursor) with command npx -y mcp-jobs and empty environment variables. No registration or API key needed.
claude_desktop_config.json
{
"mcpServers": {
"mcp-jobs": {
"command": "npx",
"args": [
"-y",
"mcp-jobs"
]
}
}
}
Fit and risk
Not for
- Scenarios requiring official API support or enterprise-grade reliability
- Compliance-sensitive use that must strictly adhere to recruitment websites' terms of service (since it uses scraping)
- Users who need global job coverage
Required permissions
- No extra permissions required, but the service accesses the internet to scrape recruitment websites
Risks and side effects
- Dependence on scraping may violate target websites' terms and risk blocking
- Data timeliness and accuracy may be affected by anti-scraping measures
- No official API, so functionality may break if website structures change
Troubleshooting
- Check that Node.js version is >= 16.0.0; ensure network connectivity; if scraping issues occur, try setting CRAWLER_HEADLESS=false for debugging or adjust CRAWLER_TIMEOUT and other environment variables.
Use cases
Quickly search for job listings in a specific city and role
Fetch job details to analyze requirements and compensation
Compare salary levels for similar roles across cities
Supported clients
Claude DesktopFull support
CursorFull support
WindsurfFull support
ClineFull support