naukri-mcp

A local MCP server for your own Naukri.com account: search jobs, view job details, save/apply to jobs, check applied jobs, read your profile, and read recruiter messages — from Claude Desktop (or any MCP-compatible client). Built on patchright (a stealth-patched Playwright) driving a real Chromium browser with a persistent, logged-in profile, so you authenticate once by hand and every tool call afterward reuses that session headlessly.

Not affiliated with, endorsed by, or supported by Naukri.com / Info Edge (India) Ltd. "Naukri" is a trademark of its respective owner, used here only to describe interoperability.

Read this before you install

• This automates your own Naukri account, under your own login. It doesn't bypass authentication or access anything you couldn't already see yourself — it drives a real browser session as you.

• Naukri's Terms of Service, like most job sites, restrict automated / bot access to accounts. Using this is a judgment call about your own account. Keep call volume reasonable — don't loop search_jobs, don't mass-apply — to avoid tripping anti-bot defenses or a manual account review. This project claims no responsibility for actions taken with it; you are responsible for how you use it and for complying with Naukri's terms.

• This never sees or handles your password. naukri_login opens a real, visible Chrome window and you log in (including any OTP) yourself; the tool only watches for the session cookie that appears afterward.

• Selectors will drift. Naukri redesigns its markup periodically, like any large site. extract.py tries a few known selector variants and falls back to raw page text rather than crashing, but expect the occasional PR to fix a broken selector after a Naukri redesign. Confirmed working end-to-end (login + get_my_profile) as of the version in this repo — see commit history / releases for what's been verified since.

Related MCP server: LinkedIn MCP

Requirements

• macOS or Linux, Python 3.10+

• Xcode Command Line Tools on macOS if you don't already have them (xcode-select --install) — python3 -m venv needs them

• ~200MB free for the Chromium build patchright downloads

1. Install

git clone https://github.com/<you>/naukri-mcp.git
cd naukri-mcp
python3 -m venv .venv
source .venv/bin/activate
pip install --upgrade pip   # old pip can't do editable installs from pyproject.toml alone
pip install -e .
python3 -m patchright install chromium

2. Register it with your MCP client

For Claude Desktop, add an entry to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or the equivalent config on your platform:

{
  "mcpServers": {
    "naukri": {
      "command": "/absolute/path/to/naukri-mcp/.venv/bin/naukri-mcp",
      "args": []
    }
  }
}

Get the absolute path with which naukri-mcp (venv activated). Restart your MCP client afterward so it picks up the new server.

3. First login

Call the naukri_login tool. A real, visible Chrome window opens at Naukri's login page; log in there yourself (including any OTP/captcha). The tool polls for up to 5 minutes and saves your session to ~/.naukri-mcp/ once it detects you're logged in. After that, naukri_session_status reports logged_in: true and every other tool runs headless.

Tool list

Naukri doesn't have a real equivalent of LinkedIn's social graph (feed, connections, employee lists), so this isn't a 1:1 port of a LinkedIn-style MCP server — apply_to_job / get_applied_jobs / save_job / get_saved_jobs reflect Naukri's actual core value (the job pipeline itself) instead.

Troubleshooting

ModuleNotFoundError: No module named 'mcp.server.fastmcp' — you have mcp 2.x, which renamed that module to mcp.server.mcpserver (MCPServer replaces FastMCP, same .tool() / .run() API). This repo already targets 2.x; if you still hit this, check pip show mcp.

A tool returns raw_text or a note instead of structured data — a selector didn't match. Open an issue with the raw_text snippet (redact anything personal) or send a PR against extract.py / tools_*.py.

License

MIT — see LICENSE.