Skip to content
MCP server

Headcount Labs

Search, count and read open jobs from employer career sites over MCP

Install
Pricing
Freemium
Platforms
API, Web
Runs
Remotely
Version
1.2.0
Listing updated
2 days ago

About Headcount Labs

Headcount Labs is a freemium MCP server for hiring and recruiting. It runs as a hosted remote server, so there is nothing to install locally.

The data comes from employers' own career sites and the hiring platforms they use, including Workday, Greenhouse, Lever, iCIMS and SmartRecruiters. Copies of the same opening are merged into one job, and each job keeps a link to the original posting. The site cites more than 7 million open jobs.

There are two doors. A public endpoint needs no sign-in or key and offers nine read-only tools; a search returns at most 250 jobs, 50 per page, and calls are limited to 20 a minute per conversation. The full endpoint uses OAuth 2.1 (PKCE and dynamic client registration) or an API key as a bearer token and adds exports, the company registry and the job change feed. The README and site disagree slightly on tool counts, so check the live tool list.

Billing counts records, meaning each job or company a successful response returns. The first 100,000 each month are free and later records cost $0.01 per 1,000. Counts, field lookups and doc searches cost nothing. Job-ad text is labelled as untrusted data that the assistant shows but should not obey.

Install

Run in a terminal

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

Add to Settings → Connectors → Add custom connector

https://api.headcountlabs.com/mcp/public
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "jobs": {
      "url": "https://api.headcountlabs.com/mcp/public"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

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

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "jobs": {
      "serverUrl": "https://api.headcountlabs.com/mcp/public"
    }
  }
}

Add to your client's MCP settings (most use this shape)

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

Tools this server provides (11)

Taken from the project documentation; the running server may differ.

search_jobs
Finds jobs by title, keywords, company, location, work arrangement, pay and dates.
get_job
Reads one job with every linked posting and source links.
count_jobs
Counts jobs matching filters, optionally grouped by employer.
market_lookup
Looks up market figures.
market_breakdown
Breaks market figures down.
salary_range
Returns salary ranges.
market_dimensions
Lists market dimensions.
list_fields
Finds the filters and job fields matching your words.
search_docs
Returns the best-matching sections of the docs.
read_file
Pages through a file previously produced for you.
set_confirmation_level
Sets how large a search must be before the agent asks first.

What it does

Public keyless endpoint
Read-only tools with no sign-in, capped at 250 jobs per search.
OAuth full server
Adds file exports, company tools, usage and the changes feed.
Duplicate merging
Copies of one opening collapse into a single job with source links.
Free counts
count_jobs, list_fields and doc search do not use records.
Confirmation for big searches
A search above your confirmation level stops so the agent asks first.
Job cards in MCP Apps
Supporting clients show cards with pay, remote and location filters.

Good for

  • Count open roles for a title in one city
  • Pull salary ranges for a job family
  • Export a set of postings for a job board
  • Track new and expired jobs through the changes feed
  • Read a single posting with every source link

Pricing

Freemium

100,000 records free each month, then $0.01 per 1,000 records

Prices change. Check headcountlabs.com before you buy.

Headcount Labs FAQ

What does it cost?

The first 100,000 records each UTC month are free, then $0.01 per 1,000. A million records is $9 per the pricing page.

Do I need an account?

Not for the public endpoint. The full server needs an OAuth sign-in or an API key.

What counts as a record?

Each job or company a successful response delivers; counts and failed requests are free.

Which clients work?

The site names Claude, ChatGPT, Grok, Codex, Cursor, VS Code and other MCP clients.

Is Headcount Labs free?

Headcount Labs has a free plan, with paid plans for more usage or features.

How do I add Headcount Labs to Claude Code?

Run this command in your terminal: claude mcp add --transport http jobs https://api.headcountlabs.com/mcp/public

What are the best alternatives to Headcount Labs?

The closest alternatives to Headcount Labs are Agent-Native Analytics, Google Ads + Meta Ads + SEO/GEO MCP, Tapetide - Indian Stock Market MCP, World Monitor and Reactive Resume.

Alternatives to Headcount Labs

  1. Open-source analytics app where an AI agent builds charts and dashboards from your data

    • Remote
    • Open source
    • 7.7K GitHub stars
    • Analytics and data
  2. Hosted MCP connector for managing Google Ads, Meta Ads, GA4 and Search Console from chat

    • 8 tools
    • Remote
    • Freemium
    • 8.1K GitHub stars
    • Marketing and SEO
  3. Indian NSE and BSE stock market data for AI assistants through 48 MCP tools

    • 17 tools
    • Remote
    • Freemium
    • 150 GitHub stars
    • Finance and payments
  4. World Monitor

    MCP server

    Live geopolitical intelligence dashboard with an API and MCP server for agents

    • Remote
    • Freemium
    • Analytics and data
  5. Reactive Resume

    MCP server

    Open-source resume and cover letter builder with job tracking and an MCP endpoint

    • Remote
    • Open source
    • Hiring and recruiting
  6. CompanyData

    MCP server

    Search and enrich company records from official registers via the CompanyData API

    • 3 tools
    • Remote
    • Paid
    • 3 GitHub stars
    • Analytics and data