Allows H-1B job searching and company sponsorship analysis through function declarations integration
Enables H-1B job search automation through OpenAPI schema integration with ChatGPT for finding sponsoring companies and analyzing visa data
Provides deployment platform for hosting the H-1B job search MCP server with automatic configuration detection
H1B Job Search MCP Server
An MCP (Model Context Protocol) server that automates H-1B job searching using U.S. Department of Labor LCA disclosure data. Built with FastMCP.
š Live Server: https://h1b-job-search-mcp.onrender.com/mcp
Features
š Download LCA Data: Automatically downloads and caches H-1B LCA disclosure data from the Department of Labor
š Smart Search: Filter H-1B sponsoring companies by job role, location, and wage
š¢ Company Analytics: Get detailed sponsorship statistics for specific companies
š Top Sponsors: List top H-1B sponsoring companies by volume
š« Agency Filtering: Automatically filter out staffing agencies to find direct employers
š Export Results: Export filtered results to CSV for easy outreach
š¾ Data Caching: Intelligent caching to avoid re-downloading large datasets
š¤ Multi-LLM Support: Works with Claude, ChatGPT, Gemini, Cursor, and Poke
š How to Use
For detailed usage examples and natural language prompts, see the Usage Guide.
Quick Examples
Just talk naturally! The ask
tool understands plain English:
"Load the latest H-1B data"
"Find software engineer jobs in California paying over 150k"
"Tell me about Google's H-1B sponsorships"
"Export data scientist positions to CSV"
Available MCP Tools
1. load_h1b_data
Download and load H-1B LCA data from the Department of Labor.
Parameters:
year
: Fiscal year (default: 2024)quarter
: Quarter 1-4 (default: 4)force_download
: Force re-download even if cached
2. search_h1b_jobs
Search for H-1B sponsoring companies by job role and location.
Parameters:
job_role
: Job title to search (e.g., "Software Engineer")city
: Work city (optional)state
: Work state code (optional, e.g., "CA")min_wage
: Minimum wage filter (optional)max_results
: Maximum results to returnskip_agencies
: Skip staffing agencies (default: true)
3. get_company_stats
Get detailed H-1B sponsorship statistics for a specific company.
Parameters:
company_name
: Company name to analyze
4. get_top_sponsors
List top H-1B sponsoring companies by application volume.
Parameters:
limit
: Number of companies to returnexclude_agencies
: Exclude staffing agencies
5. export_results
Export filtered H-1B results to a CSV file.
Parameters:
job_role
: Job title to filtercity
: City filter (optional)state
: State filter (optional)filename
: Output filenamemax_results
: Maximum results to export
6. get_available_data
Check available LCA data periods and cached files.
7. ask
(Natural Language Interface) šÆ
Talk to the H-1B search in simple English!
Usage: Just describe what you want in plain language
Examples:
"I'm a software engineer looking for jobs in the Bay Area"
"Show me data scientist positions paying over 180k"
"Which companies sponsor the most H-1B visas?"
"Tell me about Microsoft's H-1B program"
Local Development
Setup
Test with MCP Inspector
Open http://localhost:3000 and connect to http://localhost:8000/mcp
using "Streamable HTTP" transport.
Example Usage Flow
Load the data:
Tool: load_h1b_data Parameters: {"year": 2024, "quarter": 4}Search for jobs:
Tool: search_h1b_jobs Parameters: { "job_role": "Software Engineer", "state": "CA", "min_wage": 120000, "skip_agencies": true }Get company details:
Tool: get_company_stats Parameters: {"company_name": "Google"}Export results:
Tool: export_results Parameters: { "job_role": "Data Scientist", "state": "NY", "filename": "ny_data_scientists.csv" }
Deployment
Option 1: Deploy to Render
Click the "Deploy to Render" button above.
Option 2: Manual Deployment
Fork this repository
Connect your GitHub account to Render
Create a new Web Service on Render
Connect your forked repository
Render will automatically detect the
render.yaml
configuration
Your server will be available at https://your-service-name.onrender.com/mcp
Current deployment: https://h1b-job-search-mcp.onrender.com/mcp
Multi-LLM Support
This MCP server works with multiple LLM platforms. For detailed integration instructions, see docs/LLM_INTEGRATION.md.
Quick Setup by Platform
Claude Desktop
ChatGPT/OpenAI
Run server with PORT=8000 python src/server.py
and use the OpenAPI schema in config/openai_config.json.
Google Gemini
Configure with function declarations using config/gemini_config.json.
Cursor IDE
Place config/cursor_config.json in .cursor/mcp-config.json
and reload.
Interaction Poke
Use config/poke_config.json in Poke settings.
See docs/LLM_INTEGRATION.md for complete setup guides, testing procedures, and troubleshooting.
Data Source
This tool uses publicly available LCA disclosure data from the U.S. Department of Labor's Foreign Labor Certification Data Center. The data includes:
Employer information
Job titles and wages
Work locations
Case status
Contact information (when available)
Note: This data shows historical H-1B sponsorship patterns. Always verify current sponsorship policies with employers directly.
Privacy & Legal
All data used is publicly available from the U.S. Department of Labor
No private or confidential information is accessed
Use responsibly and professionally when contacting employers
Respect company communication preferences
Customization
Add custom filtering logic or additional tools by modifying src/server.py
:
Troubleshooting
Data not loading: Check your internet connection and verify the year/quarter exists
No results found: Try broader search terms or check different quarters
Memory issues: The full dataset can be large; consider using
nrows
parameter in pandasCache issues: Delete the
data_cache
directory to force fresh downloads
Contributing
Feel free to submit issues and pull requests to improve this tool!
License
MIT
This server cannot be installed
remote-capable server
The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.
Enables searching and analyzing H-1B visa sponsoring companies using U.S. Department of Labor data. Supports filtering by job role, location, and salary with natural language queries to find direct employers and export results.