workingproxysites.

Provider integration · Official publisher

Oxylabs MCP

Oxylabs MCP documents tools for Web Scraper API and AI Studio. Those product families use different credentials. The repository was archived on September 16, 2026; this page records documented setup without claiming ongoing support or a successful live connection.

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

Documentation reviewed · Next review

What you can use it for

  • Retrieve a web page with the Web Scraper API.
  • Collect parsed search results.
  • Use AI Studio browser tasks with an AI Studio key.

Documented capabilities: Web search · Scraping & extraction · Browser automation.

Account & usage

Account required
Yes
Required product
Oxylabs Web Scraper API for the included setup; AI Studio requires its own key.
Billing basis
Web Scraper API plans bill by successful results, with target and rendering affecting consumption. AI Studio has separate product usage terms. Provider pricing.
Server software license
MIT

When to choose Oxylabs MCP

A useful fit when

  • Existing Oxylabs customers matching a documented tool to a product they can access.
  • Search and page extraction using Web Scraper API credentials.

Check another approach when

  • A project that requires confirmed ongoing maintenance of this archived repository.
  • Assuming a listed AI Studio tool works with only Web Scraper API credentials.
Sources: Oxylabs official MCP repository (archived)

Connect to Oxylabs MCP

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

Hosted MCP — Web Scraper API credentials

Streamable HTTP · hosted

Endpoint
https://mcp.oxylabs.io/mcp
Authentication
X-Oxylabs-Username and X-Oxylabs-Password request headers.

Before you connect

  • Oxylabs Web Scraper API username and password.
  • A remote MCP client accepting custom headers.

Cursor mcp.json (JSON) Sources: Oxylabs official MCP repository (archived), Cursor MCP configuration reference

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

{
  "mcpServers": {
    "oxylabs": {
      "url": "https://mcp.oxylabs.io/mcp",
      "headers": {
        "X-Oxylabs-Username": "YOUR_USERNAME",
        "X-Oxylabs-Password": "YOUR_PASSWORD"
      }
    }
  }
}

Match the task to the product before calling a tool

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

  1. Discover relevant sources

    Use google_search_scraper for a bounded search. Pick source URLs that answer the research question rather than treating a result listing as the full source.

    Tools: google_search_scraper

    Sources: Oxylabs official MCP repository (archived)
  2. Retrieve and inspect page content

    Use universal_scraper for selected URLs and the required output format. Review whether rendering is needed, because target and rendering choices can affect Web Scraper API consumption.

    Tools: universal_scraper

    Sources: Oxylabs official MCP repository (archived), Oxylabs billing explanation
  3. Use AI Studio only for a matching task

    If the task needs the documented browser agent, supply the separate AI Studio credential before calling ai_browser_agent. Keep the requested interaction bounded and inspect its result.

    Tools: ai_browser_agent

    Sources: Oxylabs official MCP repository (archived)

Selected tools & example tasks

Troubleshoot the connection

A listed tool reports missing credentials.

Match the tool to its product family. Hosted HTTP can advertise tools before the required product credentials are supplied.

Sources: Oxylabs official MCP repository (archived)

Scraping works but the browser agent fails authorization.

Check X-Oxylabs-AI-Studio-Api-Key. A Web Scraper username and password do not provide AI Studio authentication.

Sources: Oxylabs official MCP repository (archived)

Limits & undocumented behavior

  • The official repository was archived on 2026-09-16. Its documented hosted endpoint has not been connection-tested by WPS; ongoing maintenance is unconfirmed.
  • This setup enables Web Scraper API requests. AI Studio tools require an additional X-Oxylabs-AI-Studio-Api-Key header.
  • Hosted tools may be listed without their required credentials; those calls fail until the correct product credentials are supplied.
  • The reviewed tool documentation does not establish proxy purchasing or proxy account management.

Oxylabs MCP: questions & answers

Why does the local tool list differ from the hosted list?

Local stdio registers product families based on supplied environment variables. Hosted HTTP can list tools even when matching credentials are absent. Tool discovery alone does not prove authorization.

Sources: Oxylabs official MCP repository (archived)
Does the repository archive prove the hosted endpoint is offline?

No. It establishes the repository status, not the endpoint response. WPS has checked documentation but has not tested a live authenticated connection or confirmed continued service support.

Sources: Oxylabs official MCP repository (archived)
Which credentials do Oxylabs MCP tools need?

Web Scraper API uses its username and password; AI Studio uses its own API key. Configure the credential family for the tools you intend to call.

Sources: Oxylabs official MCP repository (archived)

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. Oxylabs official MCP repository (archived)Checked · Publisher, archive notice, hosted headers, product-specific tools and MIT license
  2. Oxylabs billing explanationChecked · Web Scraper API result-based billing
  3. Cursor MCP configuration referenceChecked · Client JSON format and remote header support

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

Alternatives to Oxylabs MCP

These integrations share documented capabilities with Oxylabs 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
Web search · 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
Web search · 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
Web search · 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 →

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