What is job-hunt-mcp?

Rules for using a job-application tracking service through MCP. They distinguish a job posting from an application record and describe how the service authenticates and handles common tracking tasks.

Use them when tracking job searches, applications, postings, interview schedules, application status, resumes, or cover letters through the connected service.

They prevent an agent from confusing saved opportunities with submitted applications or following an authentication process that does not work.

job-hunt-mcp — Skill for Claude Code and Codex by dfrysinger

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add dfrysinger/ai-job-hunt-toolkit --skill job-hunt-mcp

Clone the repo

git clone --depth 1 https://github.com/dfrysinger/ai-job-hunt-toolkit

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/dfrysinger/ai-job-hunt-toolkit/job-hunt-mcp/github.svg)](https://agentmods.dev/skills/dfrysinger/ai-job-hunt-toolkit/job-hunt-mcp)

Your own site

<a href="https://agentmods.dev/skills/dfrysinger/ai-job-hunt-toolkit/job-hunt-mcp"><img src="https://agentmods.dev/badge/skills/dfrysinger/ai-job-hunt-toolkit/job-hunt-mcp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/dfrysinger/ai-job-hunt-toolkit/job-hunt-mcp"><img src="https://agentmods.dev/badge/skills/dfrysinger/ai-job-hunt-toolkit/job-hunt-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 821 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00103	$0.00821
Opus 5	$0.00051	$0.00411
Sonnet 5	$0.00021	$0.00164
Haiku 4.5	$0.00010	$0.00082

Measured 12d ago against content hash e32b97a04d72, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

job-hunt-mcp scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Then offer to query the database directly via curl as a workaround if they need data now.

skills/job-hunt-mcp/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The mcp__job-hunt__* tools are well-documented in their schemas -- read those for parameters and usage. This skill covers the things agents consistently get wrong.

When the MCP server shows "requires authentication"

The job-hunt MCP uses API key auth, NOT OAuth. The mcp__job-hunt__authenticate tool will always fail because there is no OAuth flow to complete. Do not tell the user to "run /mcp and authenticate manually" -- that does not work either.

If you see only mcp__job-hunt__authenticate and no other mcp__job-hunt__* tools, the MCP server connection is broken. Tell the user:

"The job-hunt MCP server isn't connected. Try opening /mcp, disabling the job-hunt server, then re-enabling it. That usually reconnects it."
If that doesn't work, they may need to restart Claude Code.
Then offer to query the database directly via curl as a workaround if they need data now.

The server URL with key is: [YOUR_SUPABASE_URL]/functions/v1/job-hunt-mcp?key=[YOUR_API_KEY]

Postings and applications are separate things

A job posting is a role the user is interested in. An application is a record that the user has (or intends to) apply. These are independent:

"Add this job to my pipeline" = add_job_posting only. Do NOT also create an application. The user is just bookmarking it.
"I applied to this" = find the posting, then submit_application with status: "applied".
"I haven't actually applied to this" or "un-apply" = delete_application (keeps the posting). There is no "not applied" status -- you delete the application record.

Status flow

draft -> ready -> applied -> screening -> interviewing -> offer -> accepted
                                                              -> rejected
                                                     -> withdrawn (at any point)

draft: The initial status when an application is created before the resume has been reviewed. Typically set by the resume-optimizer agent.
ready: Resume reviewed, not yet applied. Use this (not "draft") when creating applications manually.
Statuses only move forward. Don't skip steps (e.g., don't go straight from "applied" to "offer").

Read the full file on GitHub · 54 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

12d ago First seen · 54 lines · 103 tokens per session scan A e32b97a04d72

Subscribe to this mod's changes

job-hunt-mcp is a skill published in the GitHub repository dfrysinger/ai-job-hunt-toolkit (11 stars, last pushed 4mo ago), licensed MIT. It adds 103 tokens to every session and 821 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Productivity

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

job-hunt-mcp