Skip to content
Headcount Labs logo

Headcount Labs MCP server

Which MCP servers are Headcount Labs's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-27

← Back to Headcount Labs

Whose server it is
  • Registry namecom.headcountlabs/jobsverified in the MCP registry

The registry name sits under headcountlabs.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-27
  • Stateanswerschecked 2026-10-27
  • Tools9
  • Server calls itselfheadcountlabs
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 766 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.
  • Checked on 1 of the 7 days it takes to judge reliability.

Once connected

  • For "give an AI agent a job search tool over MCP", the likely first call is search_docs.
  • Parameters are untyped or undescribed in 5 of 9 tools: check arguments before calling.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 1, the first on 2026-10-27
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
  • Answeredmeasuring1 of the 7 daily checks it takes to print a share
  • Median first answer782 ms
  • Space in an agent's context≈ 7,076 tokensthe definitions of all its tools (9), which an agent carries on every turn
  • Tool definitionsA · 91 of 100
  • Typed results0 of 9 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 5 of 9

What an agent can do with it

  • not sure · pull deduplicated job postings for research samples
  • not sure · track posted pay by company and city
  • can do · give an AI agent a job search tool over MCP

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers9 tools · read 2026-10-27
  • search_docs

    Ask a question about Headcount Labs (filters, limits, MCP setup, errors) and get the best-matching sections of the headcountlabs.com docs, each with its URL. Works without an account.

  • search_jobs

    Search current job postings by keyword, title, company, place, pay, date and more. No account needed. Call list_fields to find the filter names. Country and employment_type accept comma-separated values or arrays and match any listed…

  • get_job

    Get a job by its job_id. No account needed. By default the answer has the same compact shape search_jobs returns (rank 1, job_id, job_ad, company_id, locations, work_arrangement, pay, posted_at, first_seen_at, posting_url, apply_url) with…

  • count_jobs

    Count the current jobs matching the filters, without listing them. This is the live count: it reads the job database as it is now, so use it for "how many jobs" and "which employers are hiring" questions, and prefer its numbers over…

  • market_lookup

    Job count, pay percentiles, share of jobs showing pay, remote/hybrid/in-person shares, posting age, new postings or top employers for up to two of title, place, company, seniority, employment_type and remote, such as the pay range for…

  • market_breakdown

    Rank the values of one dimension (by: title, state, metro, city, company, seniority, employment_type or remote) by jobs, pay or another figure, over all jobs or inside one filter, such as which states pay Software Engineers the most…

  • salary_range

    What salary to ask for: for a title, a place (default US) and an optional seniority, the 25th, 50th, 75th and 90th percentile of posted pay, the sample size and a plain recommendation. Answers come from a daily snapshot of open US jobs…

  • market_dimensions

    List what market_lookup, market_breakdown and salary_range accept: the dimensions, how many values each has and the metrics; with dimension (and optionally q) the values of that dimension, such as the metro names. No account needed.

  • list_fields

    Find the search_jobs filters and the job fields that match some keywords, with each one's type and a short description. Pass words such as ["pay", "remote"]; no keywords lists everything. kind is filter (pass it in search_jobs filters) or…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "jobs": {
      "type": "http",
      "url": "https://api.headcountlabs.com/mcp/public"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http headcountlabs https://api.headcountlabs.com/mcp/public

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://api.headcountlabs.com/mcp/public as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.