hiringindex-mcp
Search live job postings and profile a slice of the job market — pay, demand, and how long listings have sat open.
search_jobs— find individual postings by title, keyword, city, country, employer, ATS board handle, work arrangement (Remote/In Person), salary bounds, and recency; paged, up to 100 per page.job_market_insights— aggregate any slice instead of paging: counts, salary percentiles by currency, remote share, top employers, seniority and employment-type mix, city/source split.posting_age_report— age profile of a slice: median days since publication, share posted in the last week, share still open after 60 days.get_job— full detail for one posting by id, including description and apply link.
All four tools take the same filter shape, so one slice can be searched, aggregated and aged without rewriting the query. Everything is read-only and returns Markdown tables by default, or raw JSON via format: "json". Data comes straight from ten applicant tracking systems (Workday, SmartRecruiters, Greenhouse, Workable, Lever, Ashby, Recruitee, Teamtailor, Breezy, Personio); a free BASIC API key is required.
Integrates with RapidAPI as the marketplace for the HiringIndex API, using RapidAPI keys and host to authenticate and meter requests for live job posting searches, market insights, and posting age reports.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@hiringindex-mcp Show me remote Python jobs in Berlin posted this week"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
hiringindex-mcp
MCP server over live job postings. Search roles, aggregate a market slice, and see how long each listing has been sitting open.
Zero dependencies, Node ≥ 18, stdio transport.
Install
npx -y hiringindex-mcpGet a key first — it is free. The BASIC plan is $0 a month for 200 job postings and
5 insights: subscribe at https://rapidapi.com/starnikovoleg/api/hiringindex/pricing and put
the key in HIRINGINDEX_API_KEY below.
Claude Desktop / Claude Code:
{
"mcpServers": {
"hiringindex": {
"command": "npx",
"args": ["-y", "hiringindex-mcp"],
"env": { "HIRINGINDEX_API_KEY": "your-key" }
}
}
}Related MCP server: simplyapply-jobs-mcp
Tools
Tool | What it answers |
| "Show me Python data roles in Amsterdam paying over 80k" |
| "What does a data engineer earn in Berlin, and who is hiring?" |
| "Are these listings fresh, or have they been open for months?" |
| "Give me the full posting for this id" |
posting_age_report reports median age, the share posted this week and the share
still open after sixty days — the most commonly cited signal that a role is not
being actively filled. It reports the numbers; it does not pretend to know the
employer's intent.
Where this sits against what exists. A free tool, whenthisjobwasposted.com, resolves the real posting date for one URL at a time and has an MCP server of its own. If that is what you need, use it — it costs nothing. This tool answers a different question: the age distribution of an entire slice of the market, computed alongside pay and demand for the same cohort. One is a lookup, the other is an aggregate.
All four take the same filter shape, so a slice defined once can be searched, aggregated and aged without rewriting the query.
Filters
Exactly what the live index can apply (checked against the marketplace listing
on 2026-09-07, board_handle added 2026-09-08). Anything else is not a filter, and the tool schemas are closed
so a model cannot invent one.
Field | Meaning | Notes |
| job titles to match | terms shorter than 3 characters are rejected by the index |
| terms mentioned anywhere in the posting (title or description) | any keyword matches; since 2026-09-08 — before that, title only |
| city as employers write it |
|
| ISO 3166-1 alpha-2 code or an English name |
|
|
| hybrid is not a separate filter upstream |
| one employer by name | |
| one ATS board by its handle | take it from the |
| advertised salary bounds | only postings that disclose a salary match |
| published in the last N days | |
| paging, |
|
Not offered here although the index accepts them: seniority and
employment_type — their values are raw vendor strings ("Mid-Senior Level",
"FullTime"), so a model would guess spellings and silently get an empty slice;
the aggregates still report both as employers write them. Not available upstream
at all: region or state, industry.
Configuration
Variable | Default | Meaning |
| — | required; also accepts |
|
| marketplace host |
| — | set this to call our backend directly instead of the marketplace |
|
| request timeout |
Setting HIRINGINDEX_API_BASE switches auth from x-rapidapi-key to x-api-key
and skips the marketplace entirely.
Why the handshake is local
The tools call REST endpoints directly instead of proxying a remote /mcp.
The marketplace meters every request against the declared path, initialize and
tools/list included. Going through this package, the handshake never leaves the
machine and only real queries cost anything.
Output
Markdown by default — repeated fields render as tables, which costs fewer tokens
than a labelled list and stays readable for a human. Pass format: "json" on any
tool for the raw response.
Development
npm test # 16 protocol checks, no key needed
HIRINGINDEX_API_KEY=... npm test # 17 — adds live calls through the marketplaceThe test drives the server the way a real client does: writes JSON-RPC to stdin, reads from stdout.
Before publishing
Smoke test with a real key: done 2026-09-07 through the marketplace, 17/17 (search, insights, age report, single posting). Re-run before every publish.
git initand addrepositorytopackage.json.The marketplace host is final (
hiringindex.p.rapidapi.com, listing public since 2026-09-07), so the default inconfig.jswill not need a major bump.Submit to the official MCP registry (no gatekeeper), then Docker MCP Registry and the Cline marketplace.
Note on the registry listing
Across 115 job-related servers in the official registry, the description is the only thing a browsing user reads, and the ones that get installed are narrow: a country, an industry, a single job family. "Job search with AI" is indistinguishable from a dozen others. Lead with the number, the source and the tool list — and with the age angle, which nobody else has taken.
Available Tools
4 toolsget_jobFetch one postingARead-onlyIdempotent
Full detail for a single posting by its id, including the description and the application link.
Inputs: id (required), format.
job_market_insightsAggregate a slice of the job marketARead-onlyIdempotent
Counts, salary percentiles by currency, remote share, top employers, seniority and employment-type mix, city and source split for any slice of postings. Accepts the same filters as search_jobs. Use this instead of paging through results when the question is about the market rather than about individual roles.
Inputs: city, format, titles, company, +7 more.
posting_age_reportHow long these postings have been openARead-onlyIdempotent
Age profile of a slice of postings: median days since publication, share posted in the last week, and share still open after sixty days. A listing that has been open for months is the most commonly cited sign that a role is not being actively filled — this reports the numbers rather than guessing.
Inputs: city, format, titles, company, +7 more.
search_jobsSearch job postingsARead-onlyIdempotent
Search live job postings read directly from ten applicant tracking systems (Workday, SmartRecruiters, Greenhouse, Workable, Lever, Ashby, Recruitee, Teamtailor, Breezy, Personio). Returns title, employer where the ATS publishes it, location, employment type, advertised salary where disclosed, posting date and the employer's own apply link where the source carries one.
Inputs: city, page, limit, format, +9 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool targets a distinct question: individual postings, aggregate market stats, single-post detail, and posting-age distribution. The overlap between search_jobs and job_market_insights is explicitly addressed in the descriptions, so an agent can reliably select the right tool.
Two tools use an imperative verb_noun pattern (search_jobs, get_job), while the other two use descriptive noun phrases (job_market_insights, posting_age_report). This is a minor convention split, but the names are still clear and the pattern is readable.
Four tools is well-scoped for a read-only job-market data server. Each tool covers a distinct and necessary operation without redundancy or bloat.
For the stated domain of job posting search and market analysis, the surface is complete: search, detail retrieval, aggregate insights, and posting-age reporting cover the core workflows. No obvious dead ends or missing lifecycle steps exist for this read-only domain.
Maintenance
Related MCP Connectors
A jobs data API and MCP server. Every listing comes from the employer's own career site, an ATS feed or a government employment service, never resold from another board. Each row names its source and when we last confirmed the vacancy existed, and a role that disappears keeps a closure date and a reason. Six tools: search_jobs, get_job, company_hiring, market_signals, coverage, changes_since.
Live Google for Jobs postings: salary, apply links, remote and date filters. Pay per job.
Live job postings from employer career sites: search, count and compare jobs and companies.
Search a live index of millions of open jobs from employer career sites and 200+ ATS platforms.
Related MCP Servers
- AlicenseAqualityCmaintenanceEnables querying open job postings directly from company applicant-tracking systems (Greenhouse, Ashby, Lever), finding a company's job board, listing and comparing roles, and accessing salary data, all without scraping or API keys.360 PyPI1MIT
- AlicenseAqualityDmaintenanceEnables real-time job search across thousands of companies' open roles from Greenhouse, Lever, Ashby, and SmartRecruiters, with full-text filtering and company-specific queries, no API key required.2MIT
- FlicenseNot gradedqualityAmaintenanceEnables AI agents to search salary-transparent tech job postings across nine boards and eight countries, filter them by pay, remote work, tech stack, level, and language, and retrieve apply URLs or track applications. All commands are JSON-first, so duplicates and unfilterable criteria come back as data rather than errors.-

LAYIQ Jobsofficial
AlicenseNot gradedqualityCmaintenanceEnables users to search public job listings and retrieve details for individual postings from inside AI assistants, including ranked results, filters, and pagination. It is read-only and requires no account, authentication, or API key.MIT