Skip to main content
Glama
JobHunt Tracker

JobHunt Tracker

by adamwardecki

Job Tracker

CI License: MIT Node Claude Code plugin Hermes Agent Runtime deps: 0

A Claude Code (and Hermes Agent) plugin that runs a disciplined job search for one person. Every weekday it finds roles that fit your hard filters, verifies each one on the employer's own posting, dedupes against everything you have touched, and prepares tailored applications. It submits only through the employer's official apply flow, using your saved auto-apply choice or your approval for each application. It tracks replies and interviews and writes one short daily report.

The design follows one principle: fewer, better applications.

Website: jobtrackermcp.com

Setup and usage docs: jobtrackermcp.com/docs.html

Status: early, and in active development. Expect rough edges, and expect the source adapters to break when job sites change. Issues and pull requests are welcome.

What it won't do

  • Send email or LinkedIn messages. It writes drafts only, and a hook blocks every send tool.

  • Submit an application unless you enabled autonomy.auto_apply during setup or typed /job-tracker:approve <role_id> in the same session. Review first is the default.

  • Create accounts, enter passwords, solve visible CAPTCHAs, tick consent boxes, or fill personal-data fields (passport, nationality, age, gender, marital status, ID numbers).

  • Auto-apply at volume.

Related MCP server: apples-tracker

Requirements

  • Claude Code 2.1.295 or newer (the Desktop app or the CLI), or Hermes Agent.

  • Node.js 22.18 or newer. If it is missing, /job-tracker:setup offers to install it on macOS and Windows. The tracker uses the built-in node:sqlite, and Node runs the plugin's TypeScript directly. There are no runtime npm dependencies.

  • Recommended connectors: Gmail and Google Calendar.

  • Recommended browser: Claude in Chrome or the host's built-in browser.

  • Optional: a LinkedIn MCP server (read-only use: job search and inbox).

Full setup and usage instructions: jobtrackermcp.com/docs.html

Install

Claude Code:

/plugin marketplace add adamwardecki/job-tracker-mcp
/plugin install job-tracker@job-tracker-mcp
/job-tracker:setup

Hermes Agent:

git clone https://github.com/adamwardecki/job-tracker-mcp.git
cd job-tracker-mcp
plugin/scripts/hermes-install.sh

Restart Hermes and type /job-tracker:setup. Details: docs/hermes.md.

Commands

Command

What it does

/job-tracker:setup

Guided setup; resumable.

/job-tracker:sweep [--limit N]

The daily run. Applies only when you enabled autonomy.auto_apply; otherwise never submits.

/job-tracker:apply [role-id]

Verify, write, fill, read back, then submit automatically if enabled or wait for your approval.

/job-tracker:approve <role-id>

You type this on the filled form to allow one submit attempt.

/job-tracker:triage <source>

Reconcile and clean a tracker board with the delete guard.

/job-tracker:prep <company>

Interview prep from your stories.

/job-tracker:status

Pipeline summary and open items.

/job-tracker:board

Kanban board in your browser.

/job-tracker:cover-letter <role-id>

Cover letter, optionally as a one-page PDF.

/job-tracker:correct

Turn your override into a rule with a reason and example.

Your data

The tracker runs locally. A stdio server on ~/.job-tracker/tracker.db. No network listener, no token. The directory is owner-only (0700), database is 0600. Nothing is sent to the plugin's author.

Privacy policy (source).

Hooks (hard gates)

Gate

Rule

Send

Email/LinkedIn sends blocked in every session.

Submit

Needs saved autonomy.auto_apply: true or /job-tracker:approve, and a passing gate_check. Automatic submission also needs one matching scored, queued role with no open question.

Board delete

Needs a fresh JOBHUNT_TRIAGE_GUARD with ok: true.

Personal data and consent

Passport, nationality, age, DOB, gender, marital, ID fields denied; consent boxes stay unticked unless you allow them.

Stop

A sweep session cannot end until every role has an event and the report was rendered.

Development

npm run setup   # dev only: TypeScript, the Node types and Biome, installed into dev/
npm test        # tsc, then the Node and Python tests

The code is TypeScript that Node runs directly (type stripping), so there is no build step and nothing to install at runtime.

See CONTRIBUTING.md before opening a pull request.

Design choices

  1. Local only. The tracker is SQLite behind a stdio server in ~/.job-tracker.

  2. The daily run is a local scheduled task.

  3. LinkedIn is read-only and optional. Send and connect tools are blocked by a hook.

  4. Voice. write-note uses an installed humanizer or writing-style skill when present, else its own rules.

  5. Templates ship neutral. Your own values go in through setup.

License

MIT

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables an MCP-capable coding agent to run a local-first job search: recording verified opportunities in a private SQLite tracker, tracking follow-ups and outcomes, and preparing evidence-based resumes, application answers, and outreach drafts. It keeps all personal data on the user's machine and stops before submitting applications, uploading documents, or contacting anyone.
      1
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI assistants to manage job applications and companies in a local SQLite-backed tracker, including searching, creating, updating, and deleting postings and companies, plus reading and updating shared job-search context.
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Enables Claude to organize a job search by registering openings, advancing applications through a status funnel, measuring conversion rates between stages, and flagging applications that have gone quiet and need follow-up. Data is kept locally in SQLite, so no external account or server is required.
      5
      MIT