# Jobs MCP Server: Company Jobs & Tech Job Search, No Login (`conserving_celerytop/jobs-mcp-server`) Actor

Remote MCP server for Claude, Cursor and other AI agents. Two read-only tools: open jobs at the companies you name, read live from Greenhouse, Lever, Ashby, Workday and 18 more job boards, and a search of current tech jobs at 824 companies. $0.005 per tool call. Connect with your own Apify token.

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

## Pricing

from $5.00 / 1,000 tool calls

This Actor is paid per event and usage. You are charged both the fixed price for specific events and for Apify platform usage.

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

MCP server job search for AI agents: connect Claude, Cursor or any MCP client and let it look up open jobs at named companies or search tech jobs, live from career pages.

**Jobs MCP Server gives Claude and other AI agents two read-only job tools: the open jobs of companies you name, read live from their career pages, and a search of jobs open today at about 820 tech, AI, remote-first and startup companies.** It is a remote MCP server (Streamable HTTP). You connect with your own Apify API token, so every search runs in your own Apify account and we never hold your credentials.

- **Ask about named companies.** "Which data roles are open at Stripe and Datadog?" returns each job's title, location, remote or hybrid, salary when published, posted date and link.
- **Search without naming companies.** "Remote senior backend jobs posted this week" searches the job boards of about 820 companies and returns the newest matches first.
- **Page through long results.** Each result has a `nextCursor`. Claude passes it back to get the next page without running the search again.

### Tools

| Tool | What it does | Main inputs |
|---|---|---|
| `get_company_jobs` | Open jobs of 1 to 25 named companies, from Greenhouse, Lever, Ashby, Workday, Workable and 17 more job boards | `companies` (job board links, websites or names), `titleIncludes`, `location`, `remoteOnly`, `maxJobsPerCompany` (default 100) |
| `search_tech_jobs` | Jobs open today at about 820 companies in five lists: AI companies, tech companies, remote-first, tech hiring in Europe, startups | `keywords`, `location`, `remoteOnly`, `workplaceTypes`, `seniorities`, `jobFunctions`, `companyLists`, `postedSince`, `hasSalary`, `maxResults` (default 50, at most 500) |

Both tools also take `pageSize` (default 25, at most 100) and `cursor`. Both are marked read-only: they never change anything in your Apify account except starting the search runs, and they never write to a job board. Invalid input returns a message that says which field to fix.

`get_company_jobs` uses our Actor [ATS Jobs API](https://apify.com/conserving_celerytop/live-career-page-jobs-api), and `search_tech_jobs` uses [Tech Jobs Search](https://apify.com/conserving_celerytop/tech-jobs-search). Their READMEs list every field, job board and company list.

### How to connect the MCP server job search tools

You need a free Apify account and an Apify API token: open [Apify Console, Settings, API & Integrations](https://console.apify.com/settings/integrations) and copy your token. A token with limited scope works.

The server URL is the Standby URL of this Actor followed by `/mcp`. Copy it from the **Endpoints** tab of this Actor. It looks like `https://conserving-celerytop--jobs-mcp-server.apify.actor/mcp`.

#### Claude (claude.ai and Claude Desktop), as a custom connector

1. Open **Settings**, then **Connectors**, and click **Add custom connector**.
2. Name it `Jobs`, and paste the server URL.
3. Under **Advanced settings**, choose **No sign-in**. In **Request headers**, add the header `authorization` with the value `Bearer ` followed by your Apify token, and mark it required.
4. Click **Add**, then turn the connector on in a chat from the tools menu.

Request headers are in beta in Claude and not every account shows them yet. If you do not see **Request headers**, use Claude Code or another MCP client below.

#### Claude Code

```bash
claude mcp add --transport http jobs https://conserving-celerytop--jobs-mcp-server.apify.actor/mcp \
  --header "Authorization: Bearer YOUR_APIFY_TOKEN"
```

#### Other MCP clients

Any client that supports Streamable HTTP with custom headers works. A typical configuration:

```json
{
  "mcpServers": {
    "jobs": {
      "type": "http",
      "url": "https://conserving-celerytop--jobs-mcp-server.apify.actor/mcp",
      "headers": { "Authorization": "Bearer YOUR_APIFY_TOKEN" }
    }
  }
}
```

Keep your token out of shared files and screenshots. You can revoke it in Apify Console at any time.

### Try it

Ask Claude, with the connector on:

- "List the open engineering jobs at boards.greenhouse.io/stripe and jobs.lever.co/palantir."
- "Find remote data engineer jobs posted in the last 7 days, senior level."
- "Show me the next page."

### How much does it cost?

You pay three things, all in your own Apify account:

| What | Price |
|---|---|
| Each successful tool call (`tool-call`), including each further page | $0.005 |
| `get_company_jobs`: ATS Jobs API charges per company | $0.045 per company on the free plan, less on paid plans, with up to 1,000 jobs included |
| `search_tech_jobs`: Tech Jobs Search charges per matching job | $1.15 per 1,000 matching jobs on the free plan, less on paid plans |
| Apify platform usage of the server itself | The server runs with 256 MB of memory while you use it and stops after it has been idle for the idle timeout |
| Apify platform usage of the called runs | Each `get_company_jobs` run uses 256 MB and each `search_tech_jobs` run 1 GB of memory, for about 1 to 2 minutes |

Calls that fail, and calls with invalid input, are not charged by this server. Each search is capped: `get_company_jobs` cannot spend more than about $0.07 per company, and `search_tech_jobs` no more than its `maxResults` allows.

Examples on the free plan, without platform usage:

- Jobs of 3 named companies, first page: $0.005 + 3 x $0.045 = $0.14
- A search for 50 matching jobs, 2 pages: 2 x $0.005 + 50 x $0.00115 = $0.07

Apify's free plan includes $5 of credit every month.

### Limits

- Up to 25 companies per `get_company_jobs` call, up to 500 matching jobs per `search_tech_jobs` call, up to 100 jobs per page.
- A call waits at most 45 seconds, so MCP clients do not time out. A search that takes longer (a tech job search usually takes 1 to 2 minutes) returns a message with a cursor. Call the tool again with it to get the results; the search is not started or charged twice.
- Cursors work as long as your Apify plan keeps run data (7 days on the free plan).
- Jobs are the ones the company's own job board shows at the time of the call. A company whose board we cannot read is listed under `companiesWithoutJobs` with the reason.

### Privacy

The server keeps no copy of your inputs, results or token. Your token is used only by the Apify platform to run the searches in your account. [Privacy policy](https://donmangudata-ops.github.io/privacy/) and [documentation](https://donmangudata-ops.github.io/mcp/).

### Support

Email don.mangu.data@gmail.com, or open an issue on the **Issues** tab. Built by Don Mangu, the author of the Actors above. This connector is not affiliated with Anthropic or with the companies whose jobs it returns.

### Related Actors

Closest to this one:

- [ATS Jobs API (career page scraper)](https://apify.com/conserving_celerytop/live-career-page-jobs-api): open jobs of the companies you name, from Greenhouse, Lever, Ashby, Workday and 18 more job boards.
- [Tech Jobs Search](https://apify.com/conserving_celerytop/tech-jobs-search): jobs open today at 824 tech, AI, remote-first and startup companies.
- [Live Jobs HTTP API](https://apify.com/conserving_celerytop/live-jobs-http-api): the same job data in one HTTP request, for Clay, Zapier, Make and n8n.

More Actors from the same developer:

**Job data**

- [AI Jobs Search](https://apify.com/conserving_celerytop/ai-jobs-search): AI, machine learning and LLM jobs at 824 AI, tech and startup companies.
- [Software Engineer Jobs](https://apify.com/conserving_celerytop/software-engineer-jobs): software engineer and developer jobs by level and stack.
- [Greenhouse Jobs Scraper](https://apify.com/conserving_celerytop/greenhouse-jobs-api): every open job on Greenhouse job boards.
- [Lever Jobs Scraper](https://apify.com/conserving_celerytop/lever-jobs-api): every open job on Lever job boards.
- [Ashby Jobs Scraper](https://apify.com/conserving_celerytop/ashby-jobs-api): every open job on Ashby job boards, with published salaries.
- [Workday Jobs Scraper](https://apify.com/conserving_celerytop/workday-jobs-api): every open job on Workday career sites.

**Company and salary research**

- [Company Hiring Signals](https://apify.com/conserving_celerytop/company-hiring-signals): one hiring score per company from its open jobs.
- [H-1B Salary Database](https://apify.com/conserving_celerytop/h1b-perm-salary-data): what employers pay, from H-1B and PERM filings.
- [Website Tech Stack Detector](https://apify.com/conserving_celerytop/website-tech-stack-detector): the CMS, ecommerce, analytics and hosting behind websites.

**Content, media and research**

- [Audio and Podcast Transcription](https://apify.com/conserving_celerytop/audio-podcast-transcription): audio, video and podcast feeds to text and subtitles.
- [Crossref Works Search](https://apify.com/conserving_celerytop/crossref-works-search): scholarly papers, DOIs and citation counts.

### FAQ

**Which MCP clients work?** Any client that supports remote MCP servers over Streamable HTTP with a bearer token or custom header, such as Claude Desktop, Claude.ai custom connectors, Cursor and the MCP Inspector.

**Does it need my Apify token?** Yes. The token authorizes the calls and the underlying runs are billed to your Apify account. The server never stores or logs it.

**Which jobs can it find?** Open jobs on the career pages of the companies you name (Greenhouse, Lever, Ashby, Workday and more), and a search across about 820 tech, AI and startup companies.

**Why does a search return a cursor instead of results?** A tech job search takes 1 to 2 minutes. The tool answers within 45 seconds so clients do not time out; call it again with the cursor to get the results.

# Actor input Schema

## Actor input object example

```json
{}
```

# Actor output Schema

## `mcpEndpoint` (type: `string`):

Streamable HTTP MCP endpoint served by this run. For everyday use, connect to the Standby URL from the Endpoints tab instead, followed by /mcp.

# 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 = {};

// Run the Actor and wait for it to finish
const run = await client.actor("conserving_celerytop/jobs-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 = {}

# Run the Actor and wait for it to finish
run = client.actor("conserving_celerytop/jobs-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 '{}' |
apify call conserving_celerytop/jobs-mcp-server --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,conserving_celerytop/jobs-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/LMLEDb8raIJ8c0gjx/builds/QuI3Zq2Xhd6vFnSpg/openapi.json