JobSweep

Durchsuche 340.000 offene Stellen direkt auf rund 7.000 Karriereseiten von Unternehmen (Greenhouse, Lever, Ashby, Workday und über 70 weitere ATS). Duplikate wurden zusammengeführt, geschlossene Stellen entfernt und jede Stelle verlinkt auf die Seite des Arbeitgebers. Remote-Server, kein API-Schlüssel erforderlich.

Gehosteter MCP-Server

npx add-mcp 'https://jobsweep.works/mcp'

Installiert in Claude Code, Codex, Cursor und mehr

Dokumentation

Connect a client

Claude Desktop

Open Settings, then Connectors, choose Add custom connector and paste the endpoint URL.

Claude Code

claude mcp add --transport http jobsweep https://jobsweep.works/mcp

Cursor

Add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "jobsweep": {
      "url": "https://jobsweep.works/mcp"
    }
  }
}

ChatGPT

Enable developer mode in Settings, then Connectors, create a connector and paste the endpoint URL. Without a key the Free limit applies: 200 requests a day per IP address, up to 25 results per page, and shared daily caps per network.

Other clients

Any client that supports MCP over streamable HTTP can connect to the endpoint URL; clients that allow custom headers can send Authorization: Bearer <key>. The server is stateless and read-only.

Try asking

  • Find remote Python backend jobs posted this week and list the ones that show a salary.
  • Which companies hiring nurses in Berlin have the most open jobs?
  • Show me part-time or internship data jobs in Canada and summarise the top three.
  • How fresh is the JobSweep index and which platforms does it cover?

Tools

ToolWhat it does
search_jobsSearch open jobs by keywords, company, place, work mode, type and date.
get_jobFull description, source postings and change history of one job.
list_filter_valuesFilter values with job counts, and the biggest hiring companies.
search_companiesFind companies by name with their number of open jobs.
index_statsIndex size and freshness: open jobs, career sites, last crawl.
get_coverageIndexed hiring platforms with sites, jobs and last successful crawl.

Prefer plain HTTP? The same data is available from the REST API, free without a key or with higher limits on a paid plan.