Skip to directory

Scrapezy MCP

Scrapezy

Remote HTTP MCP (transport name not specified in docs)5 documented tools2

About Scrapezy MCP

A hosted MCP server for extracting structured data from public websites, running configured scrapers, monitoring jobs, and retrieving results.

What you can use it for

  • Extract structured fields from public websites
  • Run configured scrapers and retrieve job results
Connection and setup
Hosting
Remote hosted
Transport
Remote HTTP MCP (transport name not specified in docs)
Endpoint
https://mcp.scrapezy.com
Authentication
OAuth 2.0 browser authorization when a client first uses the server.

Requirements

  • Scrapezy account
  • Remote MCP client with OAuth support for the documented flow

Setup steps

  1. Add `https://mcp.scrapezy.com` as a remote MCP server.
  2. Restart or reconnect the client, start a new conversation, and complete OAuth sign-in in the browser when prompted.
  3. Verify using a simple extraction from a public page; use the job status and result retrieval tools to inspect output.
  4. Review target site access rules and Scrapezy account limits before requesting larger-scale extraction.
Tools 5

Five exact tool names enumerated in current publisher docs. Hosted OAuth is required and extraction can consume account credits.

  • start_extraction

    Extract structured data from a public website using a natural-language request.

    01
  • trigger_scraper

    Run a preconfigured Scrapezy scraper by ID.

    02
  • get_job_status

    Check the status of an extraction or scraper job.

    03
  • get_job_results

    Retrieve results from a completed job.

    04
  • get_recent_scraper_results

    Retrieve the latest results for a configured scraper.

    05
Limitations and notes
  • The docs do not publish transport details beyond the remote MCP URL.
  • The documentation suggests proxy rotation to address site rate limits; users remain responsible for respecting target-site terms and access restrictions.
Original sources
  • official documentation

    Current Scrapezy docs enumerate the same five exact hosted tools as the catalog: structured extraction, configured scraper execution, job status, result retrieval and recent scraper results. The remote endpoint uses OAuth 2.0; larger extraction may consume account credits.

Documentation checked 2026-10-28T13:26:33Z. Connection has not been runtime tested.