workingproxysites.

Provider integration · Official publisher

Scrapfly MCP

Scrapfly MCP is a hosted option for tasks that range from reading a page to capturing a rendered result. This guide starts with OAuth, then separates a simple fetch from a scrape that needs browser actions. Choose the more involved tool when the task requires it.

Server publisher: Scrapfly. Guide maintained by Working Proxy Sites.

Documentation reviewed · Next review

What you can use it for

  • Fetch a page for a research assistant.
  • Extract structured content with scraping options.
  • Capture a page or run browser interactions when required.

Documented capabilities: Scraping & extraction · Browser automation.

Account & usage

Account required
Yes
Required product
Scrapfly API account.
Billing basis
Tools use the account’s API credit pool; requested products and features determine credit consumption. Provider pricing.

When to choose Scrapfly MCP

A useful fit when

  • Fetching public page content with a remote MCP client.
  • Scraping a page that requires JavaScript or browser actions, and inspecting a screenshot.

Check another approach when

  • Comparing independent proxy providers or provisioning proxy accounts.
Sources: Scrapfly MCP tool reference

Connect to Scrapfly MCP

Choose a connection profile below and replace credential placeholders in your own MCP client. The transport describes the MCP connection.

Hosted MCP with OAuth

Streamable HTTP · hosted

Endpoint
https://mcp.scrapfly.io/mcp
Authentication
OAuth sign-in to a Scrapfly account.

Before you connect

  • Scrapfly account with available API credits.
  • An OAuth-capable remote MCP client; approve access in the browser.

VS Code .vscode/mcp.json (JSON) Sources: Scrapfly official MCP repository, Scrapfly MCP authentication, Scrapfly server transport implementation, VS Code MCP configuration

{
  "servers": {
    "scrapfly": {
      "type": "http",
      "url": "https://mcp.scrapfly.io/mcp"
    }
  }
}

Example workflow: inspect a rendered source

A suggested sequence using the documented tools. Check the connected server's tool schema before making a call.

  1. Try the page reader

    Ask for the page content using the simple page-fetch tool. Review whether the returned content includes the section you need.

    Tools: web_get_page

    Sources: Scrapfly MCP tool reference
  2. Configure browser-backed extraction

    If the content needs an interaction, use the advanced scrape options and explicitly describe the action and target field. This is a proposed workflow, not a live test of a particular website.

    Tools: web_scrape

    Sources: Scrapfly MCP tool reference
  3. Check the rendered page

    Capture a screenshot when a visual check helps explain a missing field or unexpected state. Compare it with the extracted result.

    Tools: screenshot

    Sources: Scrapfly MCP tool reference

Selected tools & example tasks

Troubleshoot the connection

The client has a URL but does not finish signing in

Complete the browser authorization step and confirm your client supports OAuth for remote MCP. The URL alone does not grant access to an account.

Sources: Scrapfly MCP authentication, VS Code MCP configuration

The available tools differ from a repository overview

Use the current tool reference and your client’s discovered tool list. The reviewed repository and documentation list different totals, so this page names selected tools rather than promising a fixed count.

Sources: Scrapfly official MCP repository, Scrapfly MCP tool reference

Limits & undocumented behavior

  • The hosted template requires completing Scrapfly’s OAuth sign-in in a supporting client.
  • The published repository and live tool reference differ in tool count; selected examples use the current documentation.
  • An account-usage tool is documented, but it does not establish proxy purchasing or proxy account management.

Scrapfly MCP: questions & answers

Do I need to paste a Scrapfly API key into this configuration?

The OAuth example does not contain an API key. You still sign into a Scrapfly account and authorize the client.

Sources: Scrapfly MCP authentication
When should I use web_scrape instead of web_get_page?

Start with web_get_page for a straightforward page read. Use web_scrape when you need detailed scraping options such as rendering, headers or browser actions.

Sources: Scrapfly MCP tool reference
Are screenshots and scraping covered by the same free MCP allowance?

MCP access does not remove the underlying account billing. Product and feature choices determine credit consumption; check the current pricing for the work you intend to run.

Sources: Scrapfly pricing

Sources & review history

This listing is documentation-confirmed. We reviewed the primary sources below; this is not a successful live connection test.

Record updated . Review due .

  1. Scrapfly official MCP repositoryChecked · Publisher, hosted endpoint and VS Code connection format
  2. Scrapfly MCP authenticationChecked · OAuth connection requirements
  3. Scrapfly server transport implementationChecked · Streamable HTTP transport implementation
  4. Scrapfly MCP tool referenceChecked · Page, scrape, screenshot and browser action capabilities
  5. Scrapfly pricingChecked · API credit billing
  6. VS Code MCP configurationChecked · HTTP connection format and OAuth support

Spotted a change? Share the source and the affected setup step in Site Feedback.

Alternatives to Scrapfly MCP

These integrations share documented capabilities with Scrapfly MCP. Compare their setup and product requirements for your task.

Bright Data MCP

Search the public web, retrieve page content and use optional browser tools through Bright Data’s hosted or local MCP integration.

Shared capabilities
Scraping & extraction · Browser automation
Connection choices
Streamable HTTP · Local stdio
Product to check
Bright Data Web Unlocker API; additional products may be used by optional tools.
Compare setup & authentication →

Evomi MCP

Inspect Evomi proxy products, targeting and usage, rotate sessions, and run scraping jobs through a local Python MCP server.

Shared capabilities
Scraping & extraction · Browser automation
Connection choices
Local stdio
Product to check
Evomi Public API access plus the proxy or Scraper API product used by the tool.
Compare setup & authentication →

Novada MCP

Search, extract pages, use browser tools and configure proxy connections through Novada’s hosted endpoint or local npm package.

Shared capabilities
Scraping & extraction · Browser automation
Connection choices
Streamable HTTP · Local stdio
Product to check
Novada account with access to the scraping, browser or proxy product selected by the tool.
Compare setup & authentication →

Oxylabs MCP

Connect an agent to Oxylabs scraping and AI Studio tools, with separate credentials for each product.

Shared capabilities
Scraping & extraction · Browser automation
Connection choices
Streamable HTTP
Product to check
Oxylabs Web Scraper API for the included setup; AI Studio requires its own key.
Compare setup & authentication →