workingproxysites.
[ new post ]
[ menu ]

directory

boards

[all]

information

Provider integration · Official publisher

ScrapingAnt MCP

ScrapingAnt MCP provides three explicit output choices for the same page. Decide whether the next step needs markup, readable structure or plain text before calling a tool. Then choose rendering and proxy settings based on the target page and credit budget.

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

Documentation reviewed · Next review

What you can use it for

  • Prepare page content for reading or analysis.
  • Retrieve HTML for markup inspection.
  • Select rendering and proxy geography for a page request.

Documented capabilities: Scraping & extraction.

Account & usage

Account required
Yes
Required product
ScrapingAnt API credits
Billing basis
MCP calls consume the account API credits. Browser rendering and proxy type affect the credit cost; the subscription supplies a credit allowance for its billing period. Provider pricing.

When to choose ScrapingAnt MCP

A useful fit when

  • Reading a known page in Markdown.
  • Tasks that need a choice between source markup and plain text.

Check another approach when

  • Expecting a search-query tool from the documented three-tool interface.
  • Treating browser rendering as a sequence of interactive browser actions.
Sources: ScrapingAnt MCP reference, ScrapingAnt MCP product guide

Connect to ScrapingAnt MCP

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

ScrapingAnt hosted MCP

Streamable HTTP · hosted

Endpoint
https://api.scrapingant.com/mcp
Authentication
Send the ScrapingAnt API key in the x-api-key header.

Before you connect

  • An account and API credential for the service.
  • A client with Streamable HTTP support.

Cursor mcp.json — replace the credential placeholder Sources: ScrapingAnt MCP reference, Cursor MCP configuration

Cursor: .cursor/mcp.json (project) or ~/.cursor/mcp.json (global). Configuration guide.

{
  "mcpServers": {
    "scrapingant-http": {
      "url": "https://api.scrapingant.com/mcp",
      "headers": {
        "x-api-key": "YOUR_SCRAPINGANT_API_KEY"
      }
    }
  }
}

Choose a format and verify the content

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

  1. Match the output to the task

    Choose Markdown for structured reading, HTML for markup inspection or text when formatting is unnecessary. Supply the target URL.

    Tools: get_web_page_markdown, get_web_page_html, get_web_page_text

    Sources: ScrapingAnt MCP product guide

  2. Set rendering deliberately

    Keep browser rendering for JavaScript content. For a static page, consider disabling it and compare the returned content before applying that setting to more URLs.

    Tools: get_web_page_markdown

    Sources: ScrapingAnt rendering reference, ScrapingAnt credit cost reference

Selected tools & example tasks

  • get_web_page_html

    Retrieve HTML from the requested URL.

    Example task: Inspect page markup.

    Sources: ScrapingAnt MCP reference
  • get_web_page_markdown

    Retrieve Markdown from the requested URL.

    Example task: Read headings and linked content.

    Sources: ScrapingAnt MCP reference
  • get_web_page_text

    Retrieve plain text from the requested URL.

    Example task: Analyze text with minimal formatting.

    Sources: ScrapingAnt MCP reference

Troubleshoot the connection

Text is missing from a page retrieved without rendering.

The content may depend on JavaScript. Enable browser rendering and compare the output with the page content you need.

Sources: ScrapingAnt rendering reference

Limits & undocumented behavior

  • The documented MCP interface exposes three page-fetching tools.
  • Browser rendering is enabled by default and affects request cost.
  • Configuration is documentation-confirmed, not connection-tested.

ScrapingAnt MCP: questions & answers

Which tool should I choose for an article summary?

Markdown usually preserves useful headings and links. Plain text is an option when that formatting is unnecessary; HTML serves markup inspection.

Sources: ScrapingAnt MCP product guide
Is residential routing required for every URL?

No. Datacenter is the documented default. Consider a different proxy type only for a target that needs it, and check the resulting credit cost.

Sources: ScrapingAnt MCP reference, ScrapingAnt credit cost reference
Are MCP calls billed differently from API calls?

The MCP guide says they consume the same API credits. Rendering and proxy choices remain part of the request cost.

Sources: ScrapingAnt MCP reference, ScrapingAnt credit cost reference

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. ScrapingAnt MCP referenceChecked · Endpoint, x-api-key authentication, tools and defaults.
  2. ScrapingAnt MCP product guideChecked · Hosted page retrieval and output format use cases.
  3. ScrapingAnt rendering referenceChecked · JavaScript rendering and static-page tradeoffs.
  4. ScrapingAnt credit cost referenceChecked · Rendering and proxy credit multipliers.
  5. Cursor MCP configurationChecked · Remote URL/header and local command configuration formats.

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

Alternatives to ScrapingAnt MCP

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

Apify MCP

Find Apify Actors, inspect their inputs and pricing, run a selected Actor, and retrieve its dataset through the official MCP server.

Shared capabilities
Scraping & extraction
Connection choices
Streamable HTTP · Local stdio
Product to check
Apify Actors and platform usage
Compare setup & authentication →

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
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 →

Crawlbase MCP

Retrieve HTML or Markdown, capture rendered pages, and revisit stored crawl results through Crawlbase tools.

Shared capabilities
Scraping & extraction
Connection choices
Local stdio
Product to check
Crawlbase Crawling API and Cloud Storage
Compare setup & authentication →

Decodo MCP

Retrieve pages, search results and supported structured targets through Decodo’s Web Scraping API.

Shared capabilities
Scraping & extraction
Connection choices
Streamable HTTP
Product to check
Decodo Web Scraping API.
Compare setup & authentication →