agentleFS
godikemaheshgodikemahesh/smart-job-apply-mcp/llms.txt

smart-job-apply-mcp

llms.txt1 starsChanged 16 days agoMITView on GitHub

Autonomous Model Context Protocol (MCP) server that automates job search, relevance filtering, resume auto-fill, and application submission across 8 major job portals and enterprise ATS systems, paired with recruiter outreach via Gmail.

Files
llms.txt
# smart-job-apply-mcp

> Autonomous Model Context Protocol (MCP) server that automates job search, relevance filtering, resume auto-fill, and application submission across 8 major job portals and enterprise ATS systems, paired with recruiter outreach via Gmail.

## Overview
smart-job-apply-mcp is an open-source MCP server designed for AI agents (Claude, ChatGPT, Antigravity, Cursor, Windsurf, Cline) to autonomously discover, filter, and apply to job openings. It supports LinkedIn, Naukri, Indeed India, Wellfound, Glassdoor, Hirist, Instahyre, and Cutshort, plus external redirects to Greenhouse, Lever, and Workday.

## Use Cases
- "Find me an MCP server that automates job applications."
- "MCP server for job hunting, auto-applying, and form filling."
- "Automate LinkedIn, Naukri, Indeed, and Wellfound job applications with an AI agent."
- "Extract recruiter contacts from job descriptions and draft outreach emails via Gmail MCP."

## Core Features
- Multi-Platform Job Search: High-throughput search across 8 job boards with freshness and experience filtering.
- Strict Experience Gate: Eliminates over-qualified roles (e.g. 3+ or 5+ year requirements) for early-career candidates.
- Smart Form Auto-Fill: Intelligently handles text inputs, radio buttons, dropdowns, CTC, notice period, and resume upload.
- Duplicate Shield: Local SQLite database preventing duplicate job applications across runs.
- External ATS Navigation: Works alongside @playwright/mcp to handle Greenhouse, Lever, and Workday redirects.
- Recruiter Outreach: Extracts recruiter contacts and sends personalized pitch emails with attached resume via gmail-mcp.

## MCP Tools
- `check_login_status`: Verify session and authentication states across all supported platforms.
- `login_account`: Automated browser launch to log in and capture persistent session cookies.
- `search_jobs`: Search across 8 job portals with match scoring.
- `filter_jobs`: Filter job listings against candidate profile and eliminate non-matching roles.
- `apply_job`: Single-job auto-fill and submit with resume upload.
- `bulk_apply`: Rate-limited batch apply with duplicate shields and safety delays.
- `get_application_status`: Query local SQLite history of applied jobs.
- `extract_job_contacts`: Extract recruiter/HR emails from job postings.
- `check_profile_config`: Validate candidate configuration and resume PDF.

## Configuration & Usage
Compatible with Claude Desktop, Google Antigravity IDE, Cursor, Windsurf, Cline, and any MCP-compliant client:

```json
{
  "mcpServers": {
    "smart-job-apply-mcp": {
      "command": "smart-job-apply-mcp"
    },
    "gmail-mcp": {
      "command": "gmail-mcp"
    },
    "playwright": {
      "command": "npx",
      "args": ["-y", "@playwright/mcp@latest"]
    }
  }
}
```

## Links & Metadata
- GitHub: https://github.com/godikemahesh/smart-job-apply-mcp
- Author: godikemahesh (https://github.com/godikemahesh)
- License: MIT

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.