Jobs Data MCP (SteadyScrape)

Jobs Data MCP: live job postings for AI agents

A remote MCP server that gives Claude, Cursor, VS Code, ChatGPT and other MCP clients live job data, collected straight from employers' own career sites rather than job-board reposts.

Endpoint (Streamable HTTP):

https://mcp.apify.com/?tools=steady-scrape/ats-job-feed,steady-scrape/career-jobs-search,steady-scrape/remote-jobs-api

The server runs on Apify's hosted MCP gateway (mcp.apify.com) with three SteadyScrape Actors preselected. Nothing to install or host.

Tools

Tool	What it does	Price
steady-scrape--ats-job-feed	Every open job from the companies you name, across Greenhouse, Lever, Ashby, Workday, Oracle HCM, SmartRecruiters, Workable, BambooHR, Personio, Rippling, Teamtailor and more. Optional "only new since last run" mode. (Store)	$0.0015 / job
steady-scrape--career-jobs-search	Keyword search ("data engineer", "nurse") across company career sites, with location, remote and date filters. (Store)	$0.002 / job
steady-scrape--remote-jobs-api	Remote jobs from employer career sites, filterable by keyword, region and recency. (Store)	$0.0015 / job
get-actor-run, get-dataset-items, get-key-value-store-record, abort-actor-run	Apify helpers for fetching larger results and managing runs	free

You pay per job returned, billed to your own Apify account. New accounts get free monthly credit (sign up).

Authentication

Either:

• OAuth: clients that support MCP OAuth (Claude.ai, VS Code, Cursor) open an Apify sign-in the first time, or
• API token: send Authorization: Bearer <APIFY_TOKEN>. Get the token from Console → Settings → API & Integrations.

Client setup

Cursor (~/.cursor/mcp.json), Windsurf, and other clients that use mcpServers:

{
  "mcpServers": {
    "jobs-data": {
      "url": "https://mcp.apify.com/?tools=steady-scrape/ats-job-feed,steady-scrape/career-jobs-search,steady-scrape/remote-jobs-api",
      "headers": { "Authorization": "Bearer <YOUR_APIFY_TOKEN>" }
    }
  }
}

VS Code (.vscode/mcp.json):

{
  "servers": {
    "jobs-data": {
      "type": "http",
      "url": "https://mcp.apify.com/?tools=steady-scrape/ats-job-feed,steady-scrape/career-jobs-search,steady-scrape/remote-jobs-api"
    }
  }
}

Claude Code:

claude mcp add --transport http jobs-data "https://mcp.apify.com/?tools=steady-scrape/ats-job-feed,steady-scrape/career-jobs-search,steady-scrape/remote-jobs-api" \
  --header "Authorization: Bearer $APIFY_TOKEN"

Claude.ai / Claude Desktop: Settings → Connectors → Add custom connector → paste the endpoint URL, then sign in to Apify.

Clients that only speak stdio:

{
  "mcpServers": {
    "jobs-data": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.apify.com/?tools=steady-scrape/ats-job-feed,steady-scrape/career-jobs-search,steady-scrape/remote-jobs-api", "--header", "Authorization:${AUTH_HEADER}"],
      "env": { "AUTH_HEADER": "Bearer <YOUR_APIFY_TOKEN>" }
    }
  }
}

Example prompts

• "Which of Stripe, Ramp and Notion are hiring data engineers right now? Give me links."
• "Find remote senior Python roles posted in the last 7 days, Europe-friendly."
• "Compare how many open engineering roles Figma and Canva have, by team."

Agents should keep requests small (for example maxJobsPerCompany or maxResults of 20–50) and use get-dataset-items to page through larger results.

Registry files

• server.json: official MCP Registry entry (io.github.steadyscrape/jobs-data-mcp)
• glama.json: Glama maintainer claim

More examples (Python, JavaScript, LangChain, CrewAI, n8n): steadyscrape-examples.

License

MIT. This repo contains configuration and docs only; the tools are paid services on Apify.