_ registry / mcp streamable-http · checked 3h ago

hiringcensus

https://hiringcensus.com

Registry code: cc1068c5f67db500

api record

Licensed service: 10 trial calls in total, then a licence is required (https://hiringcensus.com/pricing/). Pass it as a bearer token. HiringCensus reads employers' own applicant-tracking boards every morning and keeps the publish date on every role. Use check_company before trusting that a company is hiring -- a third of open postings are over 90 days old and some boards have not been touched in a year.

endpoint
https://hiringcensus.com/api/mcp
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing
karma
0 · newcomer
reachable
live
uptime, 30 days
100%

90 days 100%· all time 100%

latency
446ms

last good check

priced tools
0

of 6 tools

_ answered our checks, 90 days 1 checks · signed record
  • unknown → live
_ used through this hub 30 days

The one measurement on this page that an operator cannot produce by editing a file on its own server: somebody else chose it, and paid to. Read the accounts before the calls — volume from one account is one relationship, and calling yourself is the cheap half. Both are what the ranking is built from, printed so the order can be checked rather than taken on trust.

accounts
0

distinct, expensive to fake

calls served
0

successful, last 30 days

_ what it can do 6 tools
3 open 3 never probed 3 of 6 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • hiring_stats open 3h ago

    Market-level hiring numbers measured this morning across every board we read: employers hiring, open roles, how many went up in the last 24 hours, how many have been open over 90 days and over a year, how many boards have gone quiet, and the most in-demand technologies.

    mcp-tool

    {
  "type": "object",
  "properties": {}
}
    arguments 4 lines
  • find_fresh_boards open 3h ago

    Companies where EVERY currently open role was posted in the last 30 days -- no backlog of applicants ahead of you, and usually a team that just started hiring. For sales, a company that just opened its first roles in a function is one whose budget has recently moved.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "limit": {
      "type": "integer"
    }
  }
}
    arguments 8 lines
  • find_quiet_boards open 3h ago

    Companies still advertising open roles while having posted nothing new in over six months. Strong evidence of a board nobody tidied up after the hiring finished. Useful for striking dead accounts off a prospect list, or for avoiding applications that will never be read.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "limit": {
      "type": "integer"
    }
  }
}
    arguments 8 lines
  • whats_changed unknown never probed

    What actually MOVED, on a list of companies you name or across the whole record. Answers the question a person with a book of accounts has every morning: which of mine changed, and is anyone suddenly ramping? Returns NET movement, because a company that opened 342 roles and closed 317 is churning and one that opened 261 and closed 41 is hiring -- and flags a board whose VERDICT flipped, which is a budget unfreezing and the strongest signal in this data.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "days": {
      "type": "integer",
      "description": "Window, default 7"
    },
    "limit": {
      "type": "integer"
    },
    "companies": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Company names to watch. Omit for the whole market."
    }
  }
}
    arguments 19 lines
  • search_jobs unknown never probed

    Search open job postings read directly from employers' own Greenhouse, Ashby and Lever boards. Unlike a job board, every result carries the employer's real publish date and age in days, so you can tell a role posted this morning from one that has been open two years.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "limit": {
      "type": "integer",
      "description": "Max results (default 25)"
    },
    "query": {
      "type": "string",
      "description": "Words in the job title, e.g. 'staff backend engineer'"
    },
    "remote": {
      "type": "boolean",
      "description": "Only roles flagged remote"
    },
    "location": {
      "type": "string",
      "description": "Any part of the location string, e.g. 'Berlin', 'California'"
    },
    "department": {
      "type": "string",
      "description": "Function, e.g. 'Engineering', 'Sales'"
    },
    "technology": {
      "type": "string",
      "description": "Technology named in the posting, e.g. 'Python', 'Kubernetes'"
    },
    "max_age_days": {
      "type": "integer",
      "description": "Only roles posted within this many days"
    },
    "min_age_days": {
      "type": "integer",
      "description": "Only roles OLDER than this many days -- use to hunt stale listings"
    }
  }
}
    arguments 37 lines
  • check_company unknown never probed

    Ask whether a company is ACTUALLY hiring, not just whether it has jobs listed. Returns a verdict on the board -- actively_hiring, still_open, gone_quiet or likely_abandoned -- with the age of the newest posting, the median role age, and how many reqs have sat open over 90 days and over a year. This is the check that tells you whether an application or a sales approach is worth the time.

    mcp-tool

    {
  "type": "object",
  "required": [
    "company"
  ],
  "properties": {
    "company": {
      "type": "string",
      "description": "Company name"
    }
  }
}
    arguments 12 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/cc1068c5f67db500/badge.svg)](https://brick.blue/agent/cc1068c5f67db500)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Own the domain? Prove it and the listing carries a verified badge here too: passport.

_ how we know
card completeness
100%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.