Skip to main content
Glama

hiringpulse

hiringpulse is a small local bridge to the hosted Hiring Census MCP server, which reads hiring data straight from employers' own Greenhouse, Ashby and Lever boards. Every posting it returns carries the employer's real publish date and its age in days, so a role posted this morning looks different from one that has sat open for two years.

From that raw board data the service answers the questions a job hunt or a prospect list actually turns on: is a named company really hiring or has its board just been left standing, which boards have gone quiet, which boards are entirely fresh, what moved across a watch list or the whole market, and what the market looks like in aggregate this morning. The surface is read-only: it searches and reports, and it never submits an application, sends outreach, or contacts anyone.

The bridge keeps no hiring data of its own. It serves the upstream server's tool list locally, exactly as captured from the live endpoint, and forwards each tool call upstream, returning the result untouched.

Tools

  • search_jobs — search open postings across the boards. All arguments are optional: query (words in the job title), location (any part of the location string), remote (only roles flagged remote), department (function such as Engineering or Sales), technology (technology named in the posting), max_age_days (only roles posted within this many days), min_age_days (only roles older than this many days, for hunting stale listings) and limit (max results, default 25).

  • check_company — ask whether one company is actually hiring. Required: company. Returns a board verdict (actively_hiring, still_open, gone_quiet or likely_abandoned) with the newest posting's age, the median role age, and counts of reqs open over 90 days and over a year.

  • find_quiet_boards — companies still advertising open roles while having posted nothing new in over six months. Optional: limit.

  • find_fresh_boards — companies where every currently open role was posted in the last 30 days. Optional: limit.

  • whats_changed — net movement on a list of companies or across the whole record, flagging boards whose verdict flipped. All arguments are optional: companies (names to watch; omit for the whole market), days (window, default 7) and limit.

  • hiring_stats — market-level numbers measured this morning: employers hiring, open roles, roles posted in the last 24 hours, roles open over 90 days and over a year, boards gone quiet, and the most in-demand technologies. Takes no arguments.

Related MCP server: ats-jobs-mcp

Configuration

  • HIRINGCENSUS_MCP_URL (optional) — override the upstream endpoint. Defaults to https://hiringcensus.com/api/mcp. (The override hook is this rebuild's own labelled reconstruction.)

  • HIRINGCENSUS_API_KEY (optional) — when set, every upstream request carries an Authorization: Bearer <key> header. When it is not set, no key header is sent. (The header name is pinned by the original's registry record, which declares it optional; the Bearer scheme and this env forwarding are labelled reconstructions — the original surface was captured keyless, and the registry record notes a keyless trial allowance.)

Forwarding mechanics

On the first tool call the client opens a streamable HTTP session with the upstream: a JSON-RPC initialize request (protocolVersion 2025-03-26, clientInfo name hiringpulse), then a notifications/initialized notification, then the tools/call request carrying the caller's arguments unchanged. When the upstream answers initialize with an Mcp-Session-Id header, that value rides on every later request of the session, which is reused for the life of the process. Replies may arrive as plain JSON or as server-sent events; both are read.

Successful upstream results pass through verbatim, including any isError flag the upstream sets. Failures — a JSON-RPC error, a non-2xx status, an unreadable response, or a request that cannot be completed — come back as an isError result whose text starts with hiringpulse error: (this rendering is this rebuild's own labelled reconstruction).

CLI

Each tool is also a subcommand taking one JSON argument string:

npx @reneturcios/hiringpulse search_jobs '{"query":"staff backend engineer","location":"Berlin"}'
npx @reneturcios/hiringpulse check_company '{"company":"Acme"}'
npx @reneturcios/hiringpulse hiring_stats
npx @reneturcios/hiringpulse --version

Exit codes: 0 on success, 1 on an isError result, 2 on a usage error.

MCP server

npx -y @reneturcios/hiringpulse mcp

MCP client config:

{
  "mcpServers": {
    "hiringpulse": {
      "command": "npx",
      "args": ["-y", "@reneturcios/hiringpulse", "mcp"]
    }
  }
}

Docker

docker run -i ghcr.io/cloudcorprecords/hiringpulse
docker run --rm ghcr.io/cloudcorprecords/hiringpulse --version

The container's default command is mcp, so the first form is a stdio MCP server; any other arguments reach the CLI normally.

Development

npm install
npm run build
npm test
npm run dev

The test suite runs entirely against a stubbed JSON-RPC upstream — no live network calls.

License

MIT — see LICENSE.

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
      A
      quality
      B
      maintenance
      Scans job boards for keyword patterns that indicate buying intent, technology adoption, or team expansion. Returns structured signal data for outbound targeting.
      1
      330 npm
      2
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables users to discover applicant tracking system job boards from company domains, list open roles, detect hiring changes over time, and generate hiring summaries across multiple ATS platforms.
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Enables querying job boards for a company's open roles, pulling from Greenhouse, Workday, and an opt-in LinkedIn source and normalizing the results into one shape. It discovers boards, searches one or many companies at once, and returns full postings with title-based AI/ML and junior filtering.
      7
      MIT