# Jobs Search for AI Agents (MCP): LatAm, ATS & Remote Jobs (`datadesk-io/jobs-mcp`) Actor

Job search tools for AI agents and MCP: search_remote_jobs (Remotive, RemoteOK, WWR +4), search_ats_jobs (Greenhouse, Lever, Ashby, Workable +4), search_latam_jobs (Computrabajo, Bumeran, Get on Board +5). One normalized JSON schema. $1 per 1,000 results.

- **URL**: https://apify.com/datadesk-io/jobs-mcp.md
- **Developed by:** [DataDesk](https://apify.com/datadesk-io) (community)
- **Categories:** Jobs, AI, MCP servers
- **Stats:** 1 total users, 0 monthly users, 0.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

$1.00 / 1,000 results

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

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

## 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

## Jobs Search for AI Agents (MCP): LatAm, ATS & Remote Jobs

One Actor, three job-search **tools** built for AI agents, LLM workflows and MCP clients. Every tool returns the **same normalized JSON schema**, so an agent can mix sources without extra parsing.

| Tool (`tool` input) | What it searches |
|---|---|
| `search_remote_jobs` (default) | Remote job boards: Remotive, Remote OK, We Work Remotely, Jobicy, Himalayas, Working Nomads, Arbeitnow |
| `search_ats_jobs` | Company career pages on Workday, Greenhouse, Lever, Ashby, Workable, SmartRecruiters, Recruitee, Teamtailor, BambooHR |
| `search_latam_jobs` | Latin American boards: Computrabajo (18 countries), Multitrabajos, Bumeran, Konzerta, Laborum, ZonaJobs, Vagas.com.br, Get on Board |

All inputs are optional. Running with an empty input returns recent remote jobs in about a minute.

### Use with AI agents (MCP)

Apify's hosted MCP server exposes this Actor as a tool to any MCP client (Claude Desktop, Cursor, VS Code, OpenAI Agents, LangGraph...).

**Remote MCP endpoint** (OAuth or `Authorization: Bearer <APIFY_TOKEN>`):

```
https://mcp.apify.com?tools=datadesk-io/jobs-mcp
```

**Claude Desktop / Cursor config (local stdio):**

```json
{
  "mcpServers": {
    "jobs": {
      "command": "npx",
      "args": ["-y", "@apify/actors-mcp-server", "--tools", "datadesk-io/jobs-mcp"],
      "env": { "APIFY_TOKEN": "<your Apify token>" }
    }
  }
}
```

The agent then calls the tool with a JSON input. Examples:

```json
{"tool": "search_remote_jobs", "keywords": ["python"], "locationKeywords": ["worldwide", "latam"], "maxResults": 20}
{"tool": "search_ats_jobs", "companies": ["greenhouse:gitlab", "ashby:openai", "https://nvidia.wd5.myworkdayjobs.com/NVIDIAExternalCareerSite"], "keywords": ["engineer"], "remoteOnly": true, "maxResults": 30}
{"tool": "search_latam_jobs", "keywords": ["contador"], "countries": ["ec", "co"], "maxResults": 25}
```

Tips for agents: keep `maxResults` small (20-50) and `descriptionMaxChars` low (e.g. 500) to save context and money.

You can also call it as a plain REST API: `POST https://api.apify.com/v2/acts/datadesk-io~jobs-mcp/run-sync-get-dataset-items?token=...` with the JSON input as body.

### Input

| Field | Applies to | Default | Notes |
|---|---|---|---|
| `tool` | all | `search_remote_jobs` | Which search to run |
| `keywords` | all | remote: none (all), ATS: none, LatAm: `vendedor` | Search terms / title filter |
| `maxResults` | all | 50 | Hard cap on saved and charged results (max 1000) |
| `locationKeywords` | all | none | Location text must contain one of these |
| `postedWithinDays` | all | any | Recency filter |
| `descriptionMaxChars` | all | 1500 | 0 = no description |
| `companies` | ATS | `greenhouse:gitlab`, `lever:spotify`, `ashby:ramp` | `ats:slug` or careers URL |
| `remoteOnly` | ATS | false | |
| `countries`, `latamSources`, `location` | LatAm | `ec`; computrabajo, multitrabajos, getonbrd | |
| `remoteSources` | Remote | all 7 boards | |

### Output

One row per job: `tool, source, jobId, title, company, location, country, remote, workMode, employmentType, seniority, department, salaryMin, salaryMax, salaryCurrency, salaryText, postedAt, url, applyUrl, description, scrapedAt`. Fields not published by a source are `null`.

### Pricing

Pay per event: **$1 per 1,000 results** ($0.001 per job saved). No start fee. Runs that find 0 jobs cost nothing. `maxResults` is a hard limit, and the run stops cleanly at your spending limit.

### Notes

Data comes from public job board APIs, feeds and pages. No login. Some LatAm boards block datacenter IPs; the Actor retries through Apify Proxy when that happens.

# Actor input Schema

## `tool` (type: `string`):

Which search to run. Default: search_remote_jobs.

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

Search terms. Remote: matches title/tags/category (empty = all). ATS: keep titles containing any word. LatAm: search query per keyword (default "vendedor").

## `maxResults` (type: `integer`):

Hard cap on saved (and charged) results. Default 50.

## `locationKeywords` (type: `array`):

Keep only jobs whose location contains one of these, e.g. worldwide, latam, europe, usa, quito.

## `postedWithinDays` (type: `integer`):

Keep only jobs posted in the last N days. 0 or empty = any date.

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

'ats:slug' or careers URL, e.g. greenhouse:gitlab, lever:spotify, ashby:openai, workable:huggingface, smartrecruiters:ServiceNow, recruitee:bunq, teamtailor:career, bamboohr:miquido, workday:nvidia.wd5/NVIDIAExternalCareerSite (or paste the myworkdayjobs.com careers URL). Default: greenhouse:gitlab, lever:spotify, ashby:ramp.

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

Keep only remote company jobs.

## `countries` (type: `array`):

Country codes: ec, mx, co, pe, ar, cl, ve, gt, cr, pa, do, sv, hn, bo, py, uy, ni, pr, br. Default: ec.

## `latamSources` (type: `array`):

Default: computrabajo, multitrabajos, getonbrd.

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

e.g. guayas, quito, jalisco.

## `remoteSources` (type: `array`):

Default: all seven.

## `descriptionMaxChars` (type: `integer`):

Truncate job descriptions to keep agent context small. 0 = no description.

## Actor input object example

```json
{
  "tool": "search_remote_jobs",
  "keywords": [
    "python"
  ],
  "maxResults": 50,
  "companies": [
    "greenhouse:gitlab",
    "lever:spotify",
    "ashby:ramp"
  ],
  "remoteOnly": false,
  "countries": [
    "ec"
  ],
  "descriptionMaxChars": 1500
}
```

# Actor output Schema

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

Normalized job rows (see dataset schema for field descriptions)

# 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 = {
    "tool": "search_remote_jobs",
    "keywords": [
        "python"
    ],
    "companies": [
        "greenhouse:gitlab",
        "lever:spotify",
        "ashby:ramp"
    ],
    "countries": [
        "ec"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("datadesk-io/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 = {
    "tool": "search_remote_jobs",
    "keywords": ["python"],
    "companies": [
        "greenhouse:gitlab",
        "lever:spotify",
        "ashby:ramp",
    ],
    "countries": ["ec"],
}

# Run the Actor and wait for it to finish
run = client.actor("datadesk-io/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 '{
  "tool": "search_remote_jobs",
  "keywords": [
    "python"
  ],
  "companies": [
    "greenhouse:gitlab",
    "lever:spotify",
    "ashby:ramp"
  ],
  "countries": [
    "ec"
  ]
}' |
apify call datadesk-io/jobs-mcp --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,datadesk-io/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/u09VcpaT6sxoGAogr/builds/mFORJ1LcVXPL9j775/openapi.json