Skip to main content
Glama

ATS Career Jobs Scraper

ats_career_jobs

Scrape job listings from Greenhouse, Lever, Ashby, Workable, SmartRecruiters and Recruitee career pages by board URL or company domain, returning titles, salaries, locations and apply links.

Instructions

Scrape job listings from public ATS career pages: Greenhouse, Lever, Ashby, Workable, SmartRecruiters and Recruitee. Returns title, location, salary, department, apply URL and description via official public board APIs. Auto-detect the ATS from a company domain or pass board URLs. No login and no proxy. Use this for job search, recruiting, hiring signals and lead generation. Van Born Labs. $2.00 per 1,000 jobs, billed to your Apify account.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "ats_career_jobs"
  }
}

Input Schema

NameRequiredDescriptionDefault
boardsNoCompany career / job-board URLs, or ATS tokens/slugs. The Actor auto-detects Greenhouse, Lever, Ashby, Workable, SmartRecruiters and Recruitee from the URL. You can also write greenhouse:stripe, lever:palantir, ashby:linear, workable:huggingface, smartrecruiters:BoschGroup or recruitee:bunq. A bare slug (e.g. stripe) is probed against every supported ATS.
keywordNoKeep jobs whose title, department, team, location or description contains all of these words (case-insensitive).
maxJobsNoHard cap on the number of job listings scraped (and charged) in this run. Defaults to 10 in this MCP server to keep runs cheap.
locationNoKeep jobs whose location contains this text (e.g. London, Remote, United States).
departmentNoKeep jobs whose department or team contains this text (e.g. Engineering, Marketing).
remoteOnlyNoKeep only jobs flagged as remote (or whose workplace type is remote).
discoverOnlyNoIf enabled, only return which ATS / board token each company domain uses. Nothing is charged except the tiny start fee.
companyDomainsNoOptional helper: company websites (e.g. stripe.com or https://openai.com). The Actor looks up which ATS the company uses (slug probe + careers-page scan) and then scrapes those boards. Use Discover only to list the ATS without scraping jobs.
maxConcurrencyNoParallel HTTP requests to the official job-board APIs.
includeDescriptionNoInclude full HTML and plain-text descriptions. Turn off for a faster, lighter listing of titles and metadata. On SmartRecruiters this also avoids an extra request per job.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare openWorldHint=true and destructiveHint=false, but the description adds real context beyond them: no login and no proxy required, official public board APIs as the source, and per-job pricing ($2.00 per 1,000 jobs) with the discover-only mode carrying only a start fee. It doesn't cover failure modes (e.g. what happens when an ATS can't be detected), which keeps it at 4.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three dense sentences, front-loaded with what is scraped before use cases and commercial terms. The vendor attribution ("Van Born Labs.") is the only line that doesn't help an agent decide or invoke, a minor bit of filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 10-parameter, no-output-schema tool the description does the heavy lifting: it lists returned fields, states the auth model, and discloses the billing model. Minor omissions remain – concurrency/rate-limit implications and error behavior when a board can't be resolved are unaddressed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents all ten parameters thoroughly, including the ATS-prefix syntax and slug probing. The description restates the auto-detect capability but adds no syntax, defaults, or constraints beyond what the schema provides – baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb+resource ("Scrape job listings from public ATS career pages") and enumerates the six supported ATS platforms. It also states the returned fields, so an agent knows exactly what the tool produces without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear use-case framing ("job search, recruiting, hiring signals and lead generation") and explains the two input routes: auto-detect from a company domain or pass board URLs. It never states when NOT to use it or names an alternative path, so it falls short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.