# ATS Jobs Lookup MCP (Greenhouse, Lever, Ashby & more) (`feasible_faldstool/ats-jobs-mcp`) Actor

Give a company name or careers URL, get its open jobs in one clean format. Auto-detects the ATS and uses its official public job-board API. Built for AI agents via MCP.

- **URL**: https://apify.com/feasible_faldstool/ats-jobs-mcp.md
- **Developed by:** [jo jo](https://apify.com/feasible_faldstool) (community)
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

Pay per usage

This Actor is paid per platform usage. The Actor is free to use, and you only pay for the Apify platform usage, which gets cheaper the higher subscription plan you have.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-usage

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## ATS Jobs Lookup (MCP) — one tool for Greenhouse, Lever, Ashby, Workable, SmartRecruiters, Recruitee & Personio

**Give it a company name or careers-page URL. Get that company's open jobs back in one clean, consistent format.**

The Actor detects which applicant tracking system (ATS) the company uses and reads the ATS's **official public job-board API** (the same feed that powers the company's own careers page). No login, no captcha, no scraping of private data.

Built for **AI agents via MCP**: small inputs, flat output, short description summaries that fit in an LLM context.

### Typical agent questions it answers

- "Is Notion hiring AI engineers right now?"
- "List remote engineering roles at Spotify, Ramp and Hugging Face."
- "Which of these 20 SaaS companies are hiring sales people in Germany?" (lead generation: hiring = budget)
- "What did OpenAI post in the last week?" (sort by `postedAt`)

### Supported ATS

| ATS | Public endpoint used |
|---|---|
| Greenhouse | `boards-api.greenhouse.io/v1/boards/{slug}/jobs` |
| Lever | `api.lever.co/v0/postings/{slug}` (+ EU) |
| Ashby | `api.ashbyhq.com/posting-api/job-board/{slug}` |
| Workable | `apply.workable.com/api/v1/widget/accounts/{slug}` |
| SmartRecruiters | `api.smartrecruiters.com/v1/companies/{id}/postings` |
| Recruitee | `{slug}.recruitee.com/api/offers/` (also custom domains) |
| Personio | `{slug}.jobs.personio.de/xml` (or `.com`) |

### Input

| Field | Type | Notes |
|---|---|---|
| `companies` | string\[] **required** | Names (`"notion"`), ATS slugs (`"BoschGroup"`) or URLs (`"https://jobs.lever.co/spotify"`, `"https://www.notion.com/careers"`). URLs are most reliable. |
| `keywords` | string\[] | Keep jobs whose title/department contains any keyword. |
| `location` | string | Substring match (`"London"`, `"Germany"`); `"remote"` = remote only. |
| `remoteOnly` | boolean | Only remote jobs. |
| `maxJobs` | integer | Per company, newest first (default 50). |
| `ats` | enum | `auto` (default) or force one ATS. |
| `includeDescription` | boolean | Include ≤500-char plain-text summary (default true). |

How detection works: a URL is matched against known ATS domains; otherwise the public page HTML is checked for ATS links/embeds; otherwise the company name is tried as a slug on each ATS. Passing a plain name can occasionally hit a different company that uses the same slug — check `company`/`atsSlug`, or pass the URL.

#### Example input

```json
{
  "companies": ["notion", "https://jobs.lever.co/spotify", "https://apply.workable.com/huggingface/"],
  "keywords": ["engineer", "AI"],
  "remoteOnly": true,
  "maxJobs": 10
}
```

### Output (one dataset item per job)

```json
{
  "company": "Notion",
  "title": "Software Engineer, Mobile Core (Android)",
  "department": "Engineering",
  "location": "San Francisco, California; New York, New York",
  "remote": true,
  "postedAt": "2026-10-09T17:26:07.510Z",
  "url": "https://jobs.ashbyhq.com/notion/…",
  "descriptionSummary": "WHO WE ARE Notion is the collaborative AI workspace …",
  "ats": "ashby",
  "atsSlug": "notion"
}
```

A per-company summary (resolved ATS, total open jobs, returned count, or error) is stored in the key-value store as `SUMMARY`.

### Use from an AI agent (MCP)

Add the Apify MCP server to Claude Desktop / Cursor / any MCP client and enable this Actor:

```json
{ "mcpServers": { "apify": { "url": "https://mcp.apify.com/?tools=<username>/ats-jobs-mcp" } } }
```

Then just ask: *"Use ats-jobs-mcp to check whether Ramp has remote engineering roles."*

### Pricing (pay per event)

- **Company lookup:** $0.01 per company successfully resolved (failed lookups are free)
- **Job result:** $0.002 per job returned
- Example: 10 companies × 20 jobs = $0.10 + $0.40 = **$0.50**
- 🎉 **Free for the first two weeks after launch.**
  Use `maxJobs` and `keywords` to control cost.

### Data & compliance

- Only job postings that companies publish publicly on their own careers boards.
- No login, no captcha bypass, no private endpoints. Emails/phone numbers are stripped from summaries; no candidate or employee data is collected.
- Be gentle: one request per board (SmartRecruiters needs one extra request per returned job for descriptions).

### Run locally

```bash
npm install
apify run -p            # uses storage/key_value_stores/default/INPUT.json
## or: node test/run-tests.js   (live end-to-end tests against real companies)
```

# Actor input Schema

## `companies` (type: `array`):

Company names (e.g. "notion", "Stripe"), ATS slugs, or careers-page URLs (e.g. "https://jobs.lever.co/spotify", "https://www.notion.com/careers"). URLs are most reliable.

## `keywords` (type: `array`):

Optional. Keep jobs whose title or department contains ANY of these (case-insensitive), e.g. \["engineer", "AI"].

## `location` (type: `string`):

Optional. Substring match on location, e.g. "London", "Germany". Use "remote" to keep remote jobs only.

## `remoteOnly` (type: `boolean`):

Return only jobs flagged as remote.

## `maxJobs` (type: `integer`):

Maximum jobs returned per company (newest first). Each returned job is a billable result.

## `ats` (type: `string`):

Skip auto-detection when you already know the ATS.

## `includeDescription` (type: `boolean`):

Add a plain-text summary (max 500 chars) of each job description.

## Actor input object example

```json
{
  "companies": [
    "notion",
    "https://jobs.lever.co/spotify"
  ],
  "remoteOnly": false,
  "maxJobs": 50,
  "ats": "auto",
  "includeDescription": true
}
```

# Actor output Schema

## `results` (type: `string`):

No description

## `summary` (type: `string`):

No description

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "companies": [
        "notion",
        "https://jobs.lever.co/spotify"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("feasible_faldstool/ats-jobs-mcp").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = { "companies": [
        "notion",
        "https://jobs.lever.co/spotify",
    ] }

# Run the Actor and wait for it to finish
run = client.actor("feasible_faldstool/ats-jobs-mcp").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "companies": [
    "notion",
    "https://jobs.lever.co/spotify"
  ]
}' |
apify call feasible_faldstool/ats-jobs-mcp --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,feasible_faldstool/ats-jobs-mcp"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/CT0RSouXMbMmKjqFN/builds/TpTbUSMSASTeuwuMp/openapi.json