HireJack's MCP server provides tech job market intelligence, enabling you to search jobs, analyze companies, benchmark salaries, and gain career insights. Tools are tiered by access level:
Public Tools (no authentication required)
Search Jobs: Search live tech job postings by keyword, role, seniority, skill, location, salary, remote policy, or visa sponsorship.
Get Job: Fetch full details of a specific job posting (salary, skills, AI summary) by URL or ID.
Get Company Profile: View a company's hiring profile — tech stack, role distribution, seniority breakdown, salary medians, and hiring trends.
Search Companies: List and filter tracked companies by name, domain, or industry with hiring volume stats.
Get Market Pulse: Get a market-wide snapshot — total open jobs, top/trending skills, top hiring companies, and remote share.
Pro Tier Tools
Match Job: Score your fit against a specific job with a multi-dimension breakdown and ATS resume tips.
Company Fit: Score your fit for a company based on tech stack, roles, seniority, and hiring momentum.
Recommendations: Get personalized job recommendations ranked by composite match score.
Salary Benchmark: Compare your salary to market P10–P90 percentiles for a given role and seniority.
Skill Gap: Identify missing skills ranked by frequency in your target roles.
Market Position: Get a 0–100 market position score based on skill demand, seniority fit, and remote availability.
Skill Impact: Simulate learning new skills to see how many jobs and companies they unlock.
Watchlist Intelligence: Aggregate hiring signals (trends, top skills, salary) across all companies you're watching.
Premium Tier Tools
Resume Rewrite: Generate bullet-by-bullet resume rewrites tailored to a specific job posting.
Interview Prep: Get targeted prep materials — key topics, likely questions, and company research items.
Analyst Tier Tools
Get Company History: Monthly time-series of a company's hiring snapshots (job counts, salary, skills, seniority).
Get Skill History: Monthly adoption time-series for a skill, including company mentions and MoM deltas.
Get Market History: Daily or monthly market-wide hiring stats, remote share, and compensation trends.
Compare Companies: Side-by-side hiring comparison of up to 5 companies with monthly trajectory.
Find Companies: Multi-axis segmentation by industry, role family, skills, hiring trend, and job-count range.
Find Breakout Companies: Identify companies with extreme hiring growth exceeding a configurable threshold.
Find Emerging Skills: Discover skills with consistently growing but still low adoption — early market signals.
Find Emerging Roles: Identify roles gaining company adoption or genuinely new titles appearing in the market.
Account & Profile Tools (any authenticated account)
Save/unsave jobs, follow/unfollow companies, track job applications with pipeline status and notes.
List saved jobs, applications, and your watchlist.
View and update your profile preferences (skills, desired roles, salary, remote, seniority) to re-filter recommendations instantly.
Model Context Protocol server that exposes HireJack's tech job market intelligence to MCP-compatible clients (Claude Desktop, Claude Code, Cursor, Cline, etc.) — tech jobs, companies, skills, salaries, hiring trends.
Claude Code:
claude mcp add hirejack -- npx -y @hirejack/mcpClaude Desktop — edit ~/Library/Application Support/Claude/claude_desktop_config.json
(macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"hirejack": {
"command": "npx",
"args": ["-y", "@hirejack/mcp"]
}
}
}Restart Claude Desktop and ask away (see Example prompts).
The npm package uses stdio transport — no auth, runs locally as a subprocess, and the five public tools work out of the box.
claude.ai / Claude Desktop connector (all 31 tools): add
https://hirejack.com/api/mcp as a custom connector (Settings → Connectors →
Add custom connector), sign in with your HireJack account when prompted, and
the full Pro/Premium/Analyst intelligence surface lights up — tier-gated
server-side to your subscription.
Related MCP server: LinkedIn MCP
Job search (public, no account):
"Find remote senior backend roles paying $200K+ that sponsor visas"
"What is Stripe currently hiring? Break it down by team."
"Show me staff-level ML jobs in New York with published salary ranges"
"Which companies are hiring Rust engineers right now?"
Market research (public, no account):
"Which fintech companies are scaling hiring fastest this month?"
"What skills are trending in tech right now?"
"Compare the tech stacks of Datadog and Grafana Labs"
"What's the median advertised salary for senior data engineers?"
Career intelligence (Pro/Premium, via the hosted connector):
"Score my fit for this posting and tell me what's missing: hirejack.com/jobs/…"
"Which skill should I learn next to unlock the most jobs?"
"Where does my salary sit vs the market for staff platform engineers?"
"Rewrite my resume bullets for this Anthropic role"
Analyst (historical/segmentation, via the hosted connector):
"Which companies' hiring grew >50% in the last quarter from a real base?"
"Show Nvidia's hiring trajectory over the last 12 months"
"What skills are climbing consistently from a low base — early signals only"
Clients that support MCP prompts (Claude Desktop, Cursor) surface these as slash commands. All four are built only on the tools that work without an account, so they never dead-end on an auth error:
Prompt | Arguments | What it does |
|
| Maps a free-form ask ("remote, $200K+, Rust") onto |
|
| Resolves a name to a domain, pulls the hiring profile, then shows what is open right now. |
|
| Aggregate market picture, optionally narrowed to a role, skill or city. |
|
| What a role actually pays, using only postings that disclose a range. |
The hosted endpoint serves a different, personalized set (career check-ins, interview prep, match-scored role hunts) because those need an authenticated profile.
The server exposes HireJack's controlled vocabulary as MCP resources:
URI | Contents |
| Every skill HireJack extracts, with canonical name, id and category |
| The role taxonomy: titleId, title, family, IC/management track, typical skills |
Read these before filtering. search_jobs.skill substring-matches the
canonical names, so Kubernetes returns jobs while K8s returns none — and
update_preferences.desired_roles expects titleId values from the roles
resource.
Transport | Where | Tools available |
stdio (this package) |
| 5 public tools ( |
HTTP + OAuth 2.1 (HireJack-hosted) |
| All 31 tools, including Pro+/Analyst intelligence and account actions tied to a HireJack subscription. Implementation lives in HireJack's private Lambda; this OSS package is the stdio half. |
Public (no auth required):
Tool | Purpose |
| Search live tech job postings: role family, seniority, skill, location, salary, remote, visa, education, experience |
| Fetch one job posting by domain + jobId or HireJack URL: full details, salary, skills, AI summary |
| Full hiring profile for one company (tech stack, trends, salary, AI brief) |
| List tracked companies, filter by industry |
| Market-wide stats: totals, top skills, trending skills, top companies |
Pro tier (requires authenticated HireJack user with pro or higher):
Tool | Purpose |
| Score how well the user matches a specific job (matchPct + 5-dim breakdown + ATS tips) |
| Score the user's fit for a company (fitScore + tech-stack/role/seniority breakdown) |
| Top jobs ranked by composite match against the user's profile |
| Percentile + career-ladder benchmark vs the live market for a role/seniority |
| Compare user skills to desired-roles' market requirements; ranked missing skills |
| 0–100 market-position score (skill demand, seniority fit, remote, breadth) + matching jobs, salary median, top-aligned companies |
| Simulate learning each missing skill: jobs unlocked, boosted matches, companies needing it — ranked by impact |
| Aggregate hiring signals across every watched company: open jobs, week-over-week trend %, top skills, median salary, sparkline |
Premium tier (requires premium):
Tool | Purpose |
| Bullet-by-bullet resume rewrites tailored to a specific job |
| Targeted prep: key topics, likely questions by type, company research items |
Analyst (dedicated Analyst tier — $49/mo founding pricing; free for working journalists in exchange for a linked citation):
Tool | Purpose |
| Per-company time-series: monthly hiring snapshots + wider job-count history |
| Per-skill time-series: companyCount + jobMentions per month with MoM deltas |
| Market-wide time-series: 90 days daily or 24 months monthly |
| Up to 5 companies side-by-side: current state + monthly trajectory |
| Multi-axis segmentation: industry × family × skill × trend × job-count band |
| Companies with extreme hiring growth (% threshold + min size) |
| Skills climbing consistently across the last 3 monthly snapshots from a low base, with a real absolute company-count gain — early signal, not small-base noise (the "what should I learn before everyone else" tool) |
| Roles gaining company adoption over a tunable window (default 21 days, daily rollup) plus genuinely new titles the classifier just started seeing — the role-level companion to |
Account & profile (any authenticated HireJack account — reads and writes on the user's own data):
Tool | Purpose |
| Save a job to (or remove it from) the user's saved-jobs list |
| Follow (or unfollow) a company — powers watchlist intelligence, alerts, and the weekly digest |
| Track an application through the pipeline: applied → phone_screen → interview → offer / rejected / withdrawn, with notes |
| List the user's saved jobs (read companion to |
| List tracked applications with their pipeline stage (read companion to |
| List watched companies (read companion to |
| Read the user's profile: skills, desired roles, tier, and the matching preferences (seniority, city, remote, US-only, minimum salary) that hard-filter recommendations and alerts |
| Update matching preferences from the conversation — minimum salary, require-listed-salary, remote / US-only, seniority, city — persists to the profile and re-filters everything immediately |
Unlike the website's toggle endpoints, these use explicit, idempotent
actions (state is checked first), so an agent retrying a "save" can never
silently unsave. The write tools (save_job, watch_company,
track_application, update_preferences) are annotated readOnlyHint: false so MCP clients ask for approval appropriately.
Pro+ tools are thin wrappers over the website's existing intelligence Lambdas. Tier gating happens server-side in those Lambdas — the MCP server just forwards the user's identity. If the user lacks the required tier, the API returns 403 and the tool surfaces a clear upgrade hint.
git clone https://github.com/TVLSS/hirejack-mcp
cd hirejack-mcp
npm install
npm run build # tsc → dist/
node dist/index.js # waits on stdin/stdout for JSON-RPCPublishing is automated by GitHub Actions (.github/workflows/release.yml).
Pushing a version tag builds, publishes to npm, and updates the MCP Registry:
npm version patch # bumps package.json + creates the vX.Y.Z tag
git push && git push --tagsThe workflow verifies the tag matches package.json, then runs npm publish
(using the NPM_TOKEN repo secret) and a best-effort MCP Registry update via
GitHub OIDC. Keep server.json's version in step with package.json.
Env var | Default | Purpose |
|
| Override if you're self-hosting a fork against a different backend |
|
| Used in |
The npm package ships the stdio transport only. The hosted HTTP+OAuth
endpoint at https://hirejack.com/api/mcp is run separately by HireJack
and not implemented in this repo.
src/
├── index.ts # stdio entry point
├── registry.ts # transport-agnostic tool registry
├── prompts.ts # slash commands (public-tool-only by design)
├── resources.ts # controlled vocabulary (skills, roles)
├── lib/
│ ├── api.ts # HireJack REST client
│ ├── format.ts # tool result helpers
│ └── proAuth.ts # Pro+ auth check (returns "use hosted endpoint" in stdio)
└── tools/ # 29 files, 31 registered toolsMIT — see LICENSE.
Issues / feature requests: https://github.com/TVLSS/hirejack-mcp/issues
General feedback: https://hirejack.com/feedback.html
Site / product: https://hirejack.com
Time-series of a company's hiring profile. Analyst tier. Returns monthly snapshots (totalJobs, engineeringJobs, medianSalary, hiringTrend, trendPct, top skills, seniority + family distribution) plus the wider monthlyPostings job-count series and current-state summary. Use for 'how has Anthropic's hiring changed since January?' or 'is Stripe growing or shrinking?'. Not for a current-state snapshot (get_company_profile) or side-by-side comparison (compare_companies).
Inputs: domain (required), months. Returns: data, meta, citation_url
Fetch HireJack's full hiring profile for a single company by domain. Returns: tech stack (top skills with counts), role distribution, seniority breakdown, location breakdown, hiring trend (% MoM), salary medians where disclosed, and an AI-generated hiring brief. Use this for queries like 'what is Stripe hiring?', 'what tech does Anthropic use?', or before comparing companies. Not for historical trends (get_company_history, Analyst) or the user's personal fit (company_fit).
Inputs: domain (required). Returns: data, meta, citation_url
Fetch one job posting by domain + jobId, or by HireJack detail URL. Returns title, company, location, salary, skills, seniority, posted date, visa/remote/education metadata, and (when available) the AI summary. Use after search_jobs when the user picks a specific role to discuss, or when the user pastes a HireJack job URL. Not for browsing or filtering postings (search_jobs) or personal fit scoring (match_job).
Inputs: url, jobId, domain. Returns: data, meta, citation_url
Time-series of market-wide hiring stats: total jobs, remote share, compensation, seniority + family distribution, top skills. Analyst tier. Daily resolution back to early March 2026; monthly resolution from March 2026. Use for 'how has the market shifted in 2026?' or 'is remote hiring trending up?'. Not for the current snapshot — use get_market_pulse for that.
Inputs: days, range, detail, months. Returns: data, meta, citation_url
Time-series of a skill's market adoption. Analyst tier. Returns monthly companyCount + jobMentions for the skill, top companies hiring for it each month, and computed MoM deltas. Use for 'how fast is Rust adoption growing?' or 'is React still dominant?'. Not for discovering early-stage skills you can't yet name — use find_emerging_skills for that.
Inputs: skill (required), months. Returns: data, meta, citation_url
Generate targeted interview prep for a specific job: 5 key topics (deep vs surface depth based on job seniority), 5 likely questions by type (technical, behavioral, system design) with answer tips, and 3 company-specific research items. Premium tier. Uses job description + company tech stack + user skills as context. Use for 'help me prep for my Anthropic interview' or 'what should I expect in this loop?'. Not for resume tailoring — use resume_rewrite for that.
Inputs: url, jobId, domain. Returns: data, meta, citation_url
Compute the authenticated user's market position score (0-100). Pro tier. Weighted: 50% skill demand against current market, 20% seniority fit, 15% remote availability for the user's preference, 15% skill breadth. Returns score, matchingJobs count, salaryMedian for matching roles, per-skill demand breakdown, and the top companies whose tech stacks align best with the user's skills. Use for queries like 'how do I stack up against the market?' or 'what's my market position right now?'. Not for job-specific (match_job) or company-specific (company_fit) scores.
Inputs: no named parameters. Returns: data, meta, citation_url
Generate targeted resume bullet rewrites for a specific job, using the user's uploaded resume + the job description as context. Premium tier. Returns before/after bullet rewrites, missing keywords from the JD, and ATS-format tips. The user must have a resume uploaded to HireJack (via Settings or Onboarding). Use for 'rewrite my resume for this Stripe role' or 'tailor my bullets for this JD'. Not for interview preparation — use interview_prep for that.
Inputs: url, jobId, domain. Returns: data, meta, citation_url
Compare a salary against the live HireJack market for a role family + seniority slice. Pro tier. Returns precomputed P10/P25/P50/P75/P90 percentiles, the user's percentile ranking (when salary is supplied), and a career-ladder progression of medians by seniority. Use for 'am I paid well as a senior backend engineer?' or 'what should I ask for?'. Not for a specific job's posted range (get_job) or market-wide comp stats (get_market_pulse).
Inputs: family, salary, seniority. Returns: data, meta, citation_url
Search HireJack's database of live tech job postings. Filter by keyword, role family, seniority, skill, location, salary, remote policy, or visa sponsorship. Returns a slim list of jobs with title, company, location, salary range, posted date, and key skills. Use this for queries like 'remote senior backend roles paying $200K+', 'data engineer jobs at fintech companies', 'who is hiring Rust developers in NYC'. Not for a single known posting (get_job), company-level questions (get_company_profile), personalized ranking (recommendations), or aggregate market stats (get_market_pulse).
Inputs: q, visa, limit, skill, +12 more. Returns: data, meta, citation_url
Analyze the gap between the authenticated user's current skills and what their desired roles require in the live market. Pro tier. Returns matchPct (0-100), the list of skills the user already has that map to their target roles, and the list of missing skills ranked by impact (how often the skill appears in target-role postings). Use for 'what should I learn next?' or 'how close am I to senior PM roles?'. Not for simulating the payoff of skills the user might LEARN — use skill_impact for that.
Inputs: no named parameters. Returns: data, meta, citation_url
For each skill the authenticated user does NOT have, simulate adding it and compute the market impact. Pro tier. Returns a ranked list of skills with: newJobsUnlocked (jobs that previously didn't match but would after learning the skill), boostedJobs (existing matches that would score higher), companiesNeedingIt, relevantRoles, and a composite impactScore. Also returns profileCompleteness so the caller can suggest filling missing profile fields. Use for queries like 'what should I learn next?' or 'which skill would unlock the most jobs for me?'. Not for auditing the user's CURRENT skills against their target roles — use skill_gap for that.
Inputs: no named parameters. Returns: data, meta, citation_url
Aggregate hiring intelligence on every company the authenticated user is watching. Pro tier. For each watched company returns: totalJobs currently open, hiringTrend (up/down/stable), trendPct (week-over-week %), topSkills the company is hiring for, medianSalary, sparkline data (last ~12 weeks of job counts), and jobDelta since the previous snapshot. Use for queries like 'what's happening at the companies I'm watching?' or 'which of my watched companies are scaling up right now?'. Not for a plain list of watched companies — use list_watchlist for that.
Inputs: no named parameters. Returns: data, meta, citation_url
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 13 tools
Each tool has a distinct resource and generally clear purpose, with explicit 'not for' notes that reduce ambiguity. skill_gap vs skill_impact and market_position vs salary_benchmark are the closest pairs, but their descriptions draw adequate boundaries.
The six get_* retrieval tools follow a clear verb_noun pattern, but the rest are mixed noun phrases like salary_benchmark, skill_gap, and interview_prep, or inverted patterns like resume_rewrite. The names are readable but the convention is not uniform.
Thirteen tools is well within the ideal range and each tool earns its place for a job-search and career-intelligence platform. The set covers search, job details, company profiles, skills analysis, resume prep, interview prep, and historical analytics without feeling bloated.
Core workflows like searching jobs, viewing roles, benchmarking salary, analyzing skill gaps, and preparing for interviews are covered. However, several tools defer to tools not exposed in this server, such as get_market_pulse, list_watchlist, compare_companies, match_job, company_fit, and find_emerging_skills, creating notable dead ends.
Job platform for AI agents. Track tech jobs from companies that match your stack.
1.2M+ jobs from employer career sites, salary benchmarks and company hiring signals for AI agents.
Open jobs and hiring changes per company, daily. Free keyless lookup. AI-compiled from job boards.
Search job postings, companies, and technology stacks across 10M+ companies.
