Jobs Data MCP (SteadyScrape)

● Active

io.github.steadyscrape/jobs-data-mcp

Live job postings from 14+ ATS career sites (Greenhouse, Lever, Workday, Ashby...) and remote jobs.

Connect this server

One click to install, or copy the config below. Suits: Cursor · HTTP clients.

Add to Cursor Add to VS CodeClaude Desktop / Claude Code: paste the config below.

Or add it manually — claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor):

{
  "mcpServers": {
    "jobs-data-mcp": {
      "url": "https://mcp.steadyscrape.dev/jobs/mcp"
    }
  }
}
One line, from the terminal
Claude Code
claude mcp add --transport http jobs-data-mcp https://mcp.steadyscrape.dev/jobs/mcp
VS Code
code --add-mcp '{"name":"jobs-data-mcp","type":"http","url":"https://mcp.steadyscrape.dev/jobs/mcp"}'

Syntax from each client's docs (Claude Code: claude mcp add; Codex: codex mcp add; VS Code: code --add-mcp). Placeholders in angle brackets are values you fill in. Codex takes hosted servers in config.toml ([mcp_servers.<name>] url = …) rather than on the command line.

A starting point — check the repository for exact arguments and setup. Restart your client after editing the config.

Category
Business & CRM
Version
1.1.0
Registry
active
Published
11/20/2026
Listed in:Official MCP registry ↗how this is checked

Is it safe? Is it maintained?

Serverdex check: Nov 22, 2026

Looks healthy: Jobs Data MCP (SteadyScrape) is maintained, open source, hosted endpoint answering without a key.

Maintained
Active
Last commit today (Nov 20, 2026), 0 open issues.
Official registry
Active
Published as io.github.steadyscrape/jobs-data-mcp in the official MCP registry, version 1.1.0.
Source
Open source, MIT
Public repository under the MIT licence, 0 stars, 0 forks.
Runs
Hosted by the publisher
Your client talks to mcp.steadyscrape.dev: prompts and tool arguments leave your machine for that host.
Credentials
None needed to connect
The hosted endpoint completed the Serverdex initialize + tools/list handshake with no key (checked Nov 22, 2026); individual tools may still ask for one.
Owner
Unclaimed
Nobody has claimed this page yet; the data above comes from the registry, GitHub and the live check.

Facts only: last commit and licence from GitHub, the entry's status from the official registry, credentials from the live check. Not a code audit — run the security scan on the endpoint yourself and see the status history.

Live check

checked Nov 22, 2026, 07:08 UTCStatus history & uptime →
● Working60 msprotocol 2025-06-18v0.1.0tools

The endpoint answered the MCP handshake as "SteadyScrape Jobs Data" and listed 4 tools. Answering since Nov 21, 2026.

Context cost ≈ 1.5k tokens of tool definitions a client loads per conversation (estimate: characters ÷ 4) across 4 tools.

Tools (4)

  • company_jobs7 params

    Current open roles from 1-5 company career boards, read live from the board: title, department, location, remote flag, employment type, salary when published, posting date and job URL. Give board URLs (e.g. https://job-boards.greenhouse.io/stripe, https://jobs.lever.co/acme) or platform:slug (greenhouse:stripe). Billed per job returned.

    Show parameters
    • companiesarrayrequired1-5 career board URLs or platform:slug values.
    • keywordsarrayOptional: keep jobs whose title contains any of these.
    • locationsarrayOptional: city, region or country names or ISO codes.
    • remote_onlybooleanOnly remote jobs (default false).
    • posted_within_daysintegerOnly jobs posted in the last N days.
    • limitintegerJobs to return in total (default 20, max 50). Billed per job returned.
    • include_descriptionsbooleanInclude the first 1,500 characters of each description as plain text (default false). Not billed extra.
  • search_jobs8 params

    Search job titles across our index of company career boards (Greenhouse, Lever, Ashby, Workday and more), newest first: title, company, location, remote flag, salary when published, posting date and job URL. Filter by country, location text, remote, company and posting age. Billed per job returned.

    Show parameters
    • keywordsarrayrequired1-5 job title terms, e.g. "data engineer". A job matches if its title has all words of any term.
    • countriesarrayOptional ISO country codes or names, e.g. US, GB, Germany.
    • locationsarrayOptional location text, e.g. Berlin, New York, California.
    • companiesarrayOptional company names or board slugs.
    • remote_onlybooleanOnly remote jobs (default false).
    • posted_within_daysintegerOnly jobs posted in the last N days.
    • limitintegerJobs to return in total (default 20, max 50). Billed per job returned.
    • include_descriptionsbooleanInclude the first 1,500 characters of each description as plain text (default false). Not billed extra.
  • remote_jobs8 params

    Remote jobs from company career boards, filtered by the countries, regions or time zone the employer accepts: title, company, remote type, eligible countries and regions, seniority, salary when published, posting date and job URL. Billed per job returned.

    Show parameters
    • keywordsarrayOptional title keywords, e.g. "backend", "product designer". Empty = all remote jobs.
    • worker_countriesarrayOptional: only jobs open to workers in these countries (ISO codes or names, or EU).
    • regionsarrayOptional: e.g. Europe, EMEA, LATAM, North America.
    • worker_timezonestringOptional: your UTC offset, e.g. UTC-6 or +5:30; keeps jobs within 3 hours.
    • seniorityarrayOptional: e.g. JUNIOR, MID, SENIOR, LEAD.
    • posted_within_daysintegerOnly jobs posted in the last N days (default 14).
    • limitintegerJobs to return in total (default 20, max 50). Billed per job returned.
    • include_descriptionsbooleanInclude the first 1,500 characters of each description as plain text (default false). Not billed extra.
  • get_results3 params

    Fetch the results of a company_jobs, search_jobs or remote_jobs call that returned a run_id because it took longer than about two minutes. Returns the status while it is still running. Free: the original run is billed.

    Show parameters
    • run_idstringrequiredThe run_id from the earlier call.
    • limitintegerJobs to return (default all, up to 55).
    • include_descriptionsbooleanInclude the first 1,500 characters of each description as plain text (default false). Not billed extra.

Checked by Serverdex with a plain initialize + tools/list call to mcp.steadyscrape.dev/jobs/mcp, no credentials, about once a day. A failed check is never a removal.

On GitHub

read Nov 21, 2026
Stars
0
Forks
0
Last push
Nov 20, 2026
License
MIT

ai-agentsapifyatsjob-postingsjobsmcpmcp-servermodel-context-protocolremote-mcpweb-scraping

From the README

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): The server is hosted on the SteadyScrape MCP gateway. Tools still run in your own Apify account. Nothing to install or host. Tools 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 . Get the token from Console → Settings → API & Integrations. Client setup Cursor (~/.cursor/mcp.json), Windsurf, and other clients that use mcpServers: VS Code (.vscode/mcp.json): Claude Code: Claude.ai / Claude Desktop: Settings → Connectors → Add custom connector → paste the endpoint URL, then sign in to Apify. Clients that only speak stdio: 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…

Read the full README on GitHub →

Remotes

  • streamable-httphttps://mcp.steadyscrape.dev/jobs/mcp

The most-starred Business & CRM servers in the index, with their live-check result.

ServerStarsLast pushLive check
Contact Affordance7,477Nov 2026Working
Business Contact Finder7,470Nov 2026Working
JobSpy4,739Nov 2026Local / not checked
Relaticle1,915Nov 2026Needs sign-in
ChatbotX1,142Nov 2026Needs sign-in

Jobs Data MCP (SteadyScrape): questions people ask

Is Jobs Data MCP (SteadyScrape) a remote or a local MCP server?
According to its entry in the official MCP registry, Jobs Data MCP (SteadyScrape) ships as a hosted endpoint (streamable-http) that your client connects to by URL.
Does Jobs Data MCP (SteadyScrape) need an API key?
Its hosted endpoint completed the Serverdex live check — an MCP initialize + tools/list call — with no credentials on Nov 22, 2026. Individual tools may still ask for a key when called.
Is Jobs Data MCP (SteadyScrape) safe to use?
Looks healthy: Jobs Data MCP (SteadyScrape) is maintained, open source, hosted endpoint answering without a key. In detail — maintained: Active; official registry: Active; source: Open source, MIT; runs: Hosted by the publisher; credentials: None needed to connect. Serverdex check of Nov 22, 2026. This is a reading of the repository, the registry entry and the live check, not a code audit; run the Serverdex security scan on the endpoint before trusting it with real data.
Is Jobs Data MCP (SteadyScrape) still maintained?
Active: the repository's last commit today. Last push Nov 20, 2026, 0 GitHub stars, MIT licence. Read from GitHub on Nov 21, 2026.
What tools does Jobs Data MCP (SteadyScrape) expose?
4 tools as listed by the server itself during the live check, including company_jobs, search_jobs, remote_jobs, get_results. The full list with parameters is in the Live check section above.
How do I add Jobs Data MCP (SteadyScrape) to Claude, Cursor or VS Code?
Copy the config in "Connect this server" into your client's MCP config file (claude_desktop_config.json, ~/.cursor/mcp.json or .vscode/mcp.json), or use the one-click Add to Cursor / Add to VS Code buttons and the one-line commands for Claude Code and Codex; then restart the client.

More from steadyscrape

All 2 servers by steadyscrape →
  1. SEO Data MCP (SteadyScrape)Keyword volume, live SERP ranks, domain traffic, ranked keywords, backlinks, Google Trends, YouTube.
Browse all Business & CRM →

Add the badge to your site

Show visitors that Jobs Data MCP (SteadyScrape) is listed here — it’s also the link we check for a free listing.

Jobs Data MCP (SteadyScrape) — listed on Serverdex

HTML — for your website

<a href="https://serverdex.io/server/io-github-steadyscrape-jobs-data-mcp?utm_source=badge"><img src="https://serverdex.io/brand/badge.svg" alt="Jobs Data MCP (SteadyScrape) — listed on Serverdex" width="123" height="40" loading="lazy"></a>

Recommended. A dofollow link from your own domain is the one that counts for search engines, and it's the link we check for a free listing.

Markdown — for your README

[![Jobs Data MCP (SteadyScrape) — listed on Serverdex](https://serverdex.io/brand/badge.svg)](https://serverdex.io/server/io-github-steadyscrape-jobs-data-mcp?utm_source=badge)

Nice for visibility, but GitHub marks README links nofollow, so it doesn't pass authority. Use the HTML badge on your site as well.

Add to CursorAdd to VS CodeOpen in Claude Code

Install buttons — for your README

[![Add to Cursor](https://serverdex.io/brand/install-cursor.svg)](https://serverdex.io/install/cursor/io-github-steadyscrape-jobs-data-mcp) [![Add to VS Code](https://serverdex.io/brand/install-vscode.svg)](https://serverdex.io/install/vscode/io-github-steadyscrape-jobs-data-mcp) [![Open in Claude Code](https://serverdex.io/brand/install-claude-code.svg)](https://serverdex.io/install/claude-code/io-github-steadyscrape-jobs-data-mcp)

One click opens Cursor or VS Code with this server's config prefilled; the Claude Code button lands on the one-line command. The links point at Serverdex, so when your config changes the buttons keep working.

Install buttons — HTML for your docs

<a href="https://serverdex.io/install/cursor/io-github-steadyscrape-jobs-data-mcp"><img src="https://serverdex.io/brand/install-cursor.svg" alt="Add to Cursor — via Serverdex" width="140" height="28"></a>
<a href="https://serverdex.io/install/vscode/io-github-steadyscrape-jobs-data-mcp"><img src="https://serverdex.io/brand/install-vscode.svg" alt="Add to VS Code — via Serverdex" width="147" height="28"></a>
<a href="https://serverdex.io/install/claude-code/io-github-steadyscrape-jobs-data-mcp"><img src="https://serverdex.io/brand/install-claude-code.svg" alt="Open in Claude Code — via Serverdex" width="180" height="28"></a>

Same buttons as plain links for a docs page or website.

Prefer a live badge with the score, stars and live check? Score badge (links to a page that explains the number and back to this listing).