# Job Boards MCP Server · 35 Job Sites, 50+ Countries (`bibian/job-boards-mcp-server`) Actor

Job search MCP server for AI agents: one search_jobs tool over 35 public job boards (France Travail, Arbeitsagentur, Reed, EURES, Computrabajo, Bumeran, Job Bank, Dice, RemoteOK...) in 50+ countries plus remote. Title, company, salary, date, URL. $0.002 per job.

- **URL**: https://apify.com/bibian/job-boards-mcp-server.md
- **Developed by:** [Vivien MORVAN](https://apify.com/bibian) (community)
- **Categories:** MCP servers, Jobs, AI
- **Security:** Limited permissions
- **Stats:** 1 total users, 0 monthly users, 0.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $1.60 / 1,000 job returneds

This Actor is paid per event and usage. You are charged both the fixed price for specific events and for Apify platform usage.
Since this Actor supports Apify Store discounts, the price gets lower the higher subscription plan you have.

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

## Job Boards MCP Server · 35 Job Sites, 50+ Countries

Give your AI agent one tool to search jobs anywhere: `search_jobs` queries **35 public job boards** at once (France Travail, Arbeitsagentur, Reed, Infoempleo, jobs.ch, EURES, Computrabajo, Bumeran, Gupy, Job Bank, Dice, Built In, MyCareersFuture, RemoteOK, Remotive and more), merges the answers into one schema and removes duplicates across boards. It works in Claude, ChatGPT, Cursor, VS Code and any client that speaks MCP.

Ask your assistant things like *"find data engineer jobs in Lyon posted this week"*, *"remote Rust jobs with a salary"* or *"nursing jobs in Bavaria"*: it picks the country, calls `search_jobs` and gets back title, company, location, work mode, salary when published, date posted and the link to apply.

### Connect

Server URL (Streamable HTTP):

```
https://bibian--job-boards-mcp-server.apify.actor/mcp
```

Send your Apify API token as `Authorization: Bearer <APIFY_TOKEN>` (find it under Settings, API & Integrations in Apify Console).

Cursor, VS Code and other clients that support remote MCP servers:

```json
{
  "mcpServers": {
    "job-boards": {
      "url": "https://bibian--job-boards-mcp-server.apify.actor/mcp",
      "headers": { "Authorization": "Bearer <APIFY_TOKEN>" }
    }
  }
}
```

Claude Desktop and other clients that only run local servers can bridge it with `npx mcp-remote https://bibian--job-boards-mcp-server.apify.actor/mcp --header "Authorization: Bearer <APIFY_TOKEN>"`.

### Tools

| Tool | What it does | Price |
|---|---|---|
| `search_jobs` | Searches every default board of one country (or `REMOTE`) in parallel and returns up to 50 jobs, deduplicated across boards. | $0.002 per job returned |
| `list_job_sources` | Lists the boards, the countries each one covers and which ones run by default. | Free |

`search_jobs` arguments:

| Argument | What it does |
|---|---|
| `country` | Required. ISO code such as `FR`, `DE`, `ES`, `GB`, `IT`, `NL`, `MX`, `AR`, `BR`, `US`, `CA`, `SG`, or `REMOTE` for remote jobs worldwide. |
| `keywords` | Job title, skill or company, for example `data engineer` or `nurse`. |
| `location` | City or region inside the country, for example `Lyon` or `Berlin`. |
| `maxResults` | 20 by default, at most 50. |
| `publishedWithinDays` | Only jobs published in the last N days. |
| `remote` | `any` (default), `remote`, `hybrid` or `onsite`. |
| `sources` | Only these boards, by name from `list_job_sources`. |
| `includeDescriptions` | Adds each job description, cut to 1,500 characters. |

### Example answer

`search_jobs` with `{"country": "DE", "keywords": "Pflege", "maxResults": 2, "sources": ["arbeitsagentur"]}`, real answer of 8 November 2026:

```json
{
  "country": "DE",
  "keywords": "Pflege",
  "sources": [{ "name": "arbeitsagentur", "found": 3 }],
  "returned": 2,
  "jobs": [
    {
      "title": "Pflege (m/w/d)",
      "company": "Krankenhäuser Landkreis Freudenstadt",
      "location": "Freudenstadt, BADEN_WUERTTEMBERG",
      "country": "DE",
      "remote": "onsite",
      "employmentType": "full_time",
      "salaryMin": null,
      "salaryMax": null,
      "salaryCurrency": null,
      "salaryPeriod": null,
      "datePosted": "2026-11-06",
      "skills": [],
      "url": "https://studyflix.de/jobs/angebote/495394?l=881761&utm_source=ba",
      "source": "arbeitsagentur.de"
    },
    {
      "title": "Teamleitung Pflege (m/w/d)",
      "company": "Caritas gGmbH St. Heinrich und Kunigunde",
      "location": "Bamberg, BAYERN",
      "country": "DE",
      "remote": "onsite",
      "employmentType": "full_time",
      "datePosted": "2026-10-22",
      "url": "https://www.arbeitsagentur.de/jobsuche/jobdetail/20639-xqalo4ht1d-S",
      "source": "arbeitsagentur.de"
    }
  ]
}
```

Each answer also says how many jobs every board found and which board failed, if one did, so the agent can retry with `sources` or another country.

### Coverage

| Country | Boards searched by default |
|---|---|
| France | Free-Work, France Travail, HelloWork, Meteojob, Qapa, EURES (on request: Emploi Territorial, Choisir le Service Public) |
| Germany | Arbeitsagentur, Jobware, EURES (on request: stellenanzeigen.de) |
| United Kingdom | Reed |
| Spain | Infoempleo, Trabajos.com, Ticjob, EURES (on request: Empléate SEPE) |
| Sweden | Arbetsförmedlingen, EURES |
| Switzerland | EURES (on request: jobs.ch, best with few or no keywords) |
| Poland | EURES (on request: pracuj.pl) |
| Italy, Netherlands, Belgium, Portugal, Austria and every other EU and EEA country | EURES |
| Argentina, Chile, Peru | Bumeran network (Zonajobs, Laborum), Computrabajo, Get on Board |
| Ecuador, Panama, Venezuela | Bumeran network (Multitrabajos, Konzerta), Computrabajo |
| Mexico, Colombia | Computrabajo, Get on Board |
| Bolivia, Costa Rica, Dominican Republic, El Salvador, Guatemala, Honduras, Nicaragua, Paraguay, Puerto Rico, Uruguay | Computrabajo |
| Brazil | Gupy |
| United States (mostly tech and startup jobs) | Built In, Dice, The Muse, Wellfound, Hacker News Who is hiring |
| Canada | Job Bank |
| Singapore | MyCareersFuture |
| Remote, worldwide | RemoteOK, Remotive, We Work Remotely, Working Nomads, Jobicy, Hacker News Who is hiring, Wellfound |

### Pricing

**$0.002 per job returned**, so a 20-job answer costs $0.04. A search that finds nothing, fails or hits your spending limit adds nothing, and `list_job_sources` is free. The only other charge is a **$0.005 start fee** each time the server starts a session for you: your first call, then about every 100 seconds while you keep calling, or after a minute without calls. Set a maximum cost in your Apify account and the server never returns more jobs than it covers.

### Good to know

- **Live data.** Every call reads the boards at that moment: no stale cache, no database to sync.
- **Fast enough for a conversation.** Boards are queried in parallel, each one capped at 25 seconds; most answers come back in 2 to 10 seconds.
- **No personal data.** Only job postings are returned: no recruiter or candidate names, e-mails or phone numbers.
- **No login on the job boards**, public pages and public APIs only.
- **Normal runs work too.** Start the Actor with the same fields as input and the jobs land in a dataset you can export as JSON, CSV or Excel, or schedule daily.
- **Missing a board, a country or a field?** Open an issue in the Issues tab and say what you need. Requests are read, and the most asked ones are built next.

### The same boards as classic scrapers

Prefer batch runs and larger volumes? Each pack is also a regular Actor: [France Jobs](https://apify.com/bibian/france-jobs-scraper), [Europe Jobs](https://apify.com/bibian/europe-jobs-scraper), [Latin America Jobs](https://apify.com/bibian/latin-america-jobs-scraper), [North America Jobs](https://apify.com/bibian/north-america-jobs-scraper), [Remote Jobs Worldwide](https://apify.com/bibian/remote-jobs-worldwide-scraper) and [Asia Pacific Jobs](https://apify.com/bibian/asia-pacific-jobs-scraper).

# Actor input Schema

## `country` (type: `string`):

Country to search, or Remote for remote jobs worldwide.

## `keywords` (type: `string`):

Job title, skill or company, for example "data engineer" or "nurse". Leave empty for the latest postings.

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

City or region inside the country, for example "Lyon". Matched by each board its own way.

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

How many jobs to return (each one is charged).

## `publishedWithinDays` (type: `integer`):

Only jobs published in the last N days.

## `remote` (type: `string`):

Keep only remote, hybrid or on-site jobs.

## `sources` (type: `array`):

Limit the search to these boards. Leave empty to use every default board of the country.

## `includeDescriptions` (type: `boolean`):

Add each job description, cut to 1,500 characters.

## Actor input object example

```json
{
  "country": "FR",
  "keywords": "data engineer",
  "maxResults": 20,
  "remote": "any",
  "includeDescriptions": false
}
```

# Actor output Schema

## `jobs` (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 = {
    "country": "FR",
    "keywords": "data engineer",
    "maxResults": 20
};

// Run the Actor and wait for it to finish
const run = await client.actor("bibian/job-boards-mcp-server").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 = {
    "country": "FR",
    "keywords": "data engineer",
    "maxResults": 20,
}

# Run the Actor and wait for it to finish
run = client.actor("bibian/job-boards-mcp-server").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 '{
  "country": "FR",
  "keywords": "data engineer",
  "maxResults": 20
}' |
apify call bibian/job-boards-mcp-server --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,bibian/job-boards-mcp-server"
        }
    }
}
```

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/bNE8Xv4FucZ2ANsyC/builds/0rXUYdvNeEjWimiaw/openapi.json