mcpSource-backedReview first Safety ✓ Privacy ✓

Oxylabs MCP Server for Claude

Scrape any website, extract structured data, and search Google and Amazon from Claude — with the official Oxylabs MCP server providing universal web scraping with JS rendering, CAPTCHA bypass, AI-powered data extraction, and AI browser automation in one tool.

by Oxylabs·added 2026-06-18·

Claude Code Codex Cursor Claude Desktop

HarnessClaude CodeCodexCursorClaude Desktop

Install

Source

claude mcp add oxylabs -e OXYLABS_USERNAME=<username> -e OXYLABS_PASSWORD=<password> -- uvx oxylabs-mcp

Readiness

TrustReview first
Sourcesource-backed
Safety notesPresent
ReviewedYes

Documentation Source repository Registry JSON · LLM text

Review first — review before installing

Open the source and read safety notes before installing.

Safety notes

All scraping requests are proxied through Oxylabs infrastructure — your real IP is never exposed to target sites.
AI browser agent and AI crawler tools issue real web requests against target domains; ensure scraping complies with target site terms of service.

Privacy notes

Page content scraped from target sites is returned in Claude's context — treat sensitive competitor data or personal data in scraped results accordingly.
Your `OXYLABS_USERNAME` and `OXYLABS_PASSWORD` authenticate to the Oxylabs Web Scraper API — keep them in the MCP config env.

Prerequisites

An Oxylabs account with Web Scraper API access — sign up at oxylabs.io.
Web Scraper API username and password from your Oxylabs dashboard.
Python with `uvx` available.
An MCP client such as Claude Code or Claude Desktop.

Schema details

Install type: cli
Troubleshooting: No

Source repository stats

Scope: Source repo

Collection metadata

Estimated setup: 5 minutes
Difficulty: beginner

Tool listing metadata

Website: https://oxylabs.io
Disclosure: Oxylabs is a commercial web scraping infrastructure provider. The MCP server is officially maintained by Oxylabs.

Full copyable content

{
  "mcpServers": {
    "oxylabs": {
      "command": "uvx",
      "args": ["oxylabs-mcp"],
      "env": {
        "OXYLABS_USERNAME": "<username>",
        "OXYLABS_PASSWORD": "<password>"
      }
    }
  }
}

About this resource

Overview

The Oxylabs MCP Server is the official Model Context Protocol server from Oxylabs, the web scraping infrastructure provider. It gives Claude the ability to scrape any website with JavaScript rendering and CAPTCHA bypass, extract structured data using AI, search Google and Amazon, and automate browser tasks — all through Oxylabs' proxy infrastructure. Licensed under MIT.

Two credential sets are available; configure only one:

Web Scraper API — OXYLABS_USERNAME + OXYLABS_PASSWORD (classic proxy-based scraping)
AI Studio — OXYLABS_AI_STUDIO_API_KEY (AI-powered extraction, browser agent, AI search)

Key capabilities

Universal scraping — scrape any URL with JS rendering, stealth mode, and CAPTCHA handling.
Google Search scraping — structured SERP results, local results, images, news.
Amazon scraping — search results and product detail pages with parsed structured data.
AI extraction — AI-powered structured data extraction from arbitrary web pages.
AI crawler — crawl entire sites with AI guidance.
AI browser agent — autonomous browser automation for complex multi-step tasks.
AI search — web-wide AI-powered search with result synthesis.

Tools

Tool	Purpose
`universal_scraper`	Scrape any URL with JS rendering + CAPTCHA bypass
`google_search_scraper`	Fetch Google Search results as structured data
`amazon_search_scraper`	Scrape Amazon search result pages
`amazon_product_scraper`	Scrape Amazon product detail pages
`ai_scraper`	AI-powered structured extraction from any page
`ai_crawler`	AI-guided site crawling
`ai_browser_agent`	Autonomous multi-step browser automation
`ai_search`	Web-wide AI search with synthesis

How it compares

Server	JS rendering	CAPTCHA bypass	SERP scraping	AI extraction	Notes
Oxylabs MCP	Yes	Yes	Yes	Yes	Proxy-backed, official
Bright Data MCP	Yes	Yes	Yes	Yes	Also proxy-backed, official
Firecrawl MCP	Yes	Partial	No	Yes	Markdown extraction focus
Apify MCP	Yes	Yes	Limited	Yes	Actor-based ecosystem

Oxylabs and Bright Data are the two proxy-backed commercial web scraping MCP servers; both handle JS rendering and CAPTCHA bypass at scale.

Installation

Claude Code (Web Scraper API)

claude mcp add oxylabs \
  -e OXYLABS_USERNAME=<username> \
  -e OXYLABS_PASSWORD=<password> \
  -- uvx oxylabs-mcp

Claude Code (AI Studio)

claude mcp add oxylabs \
  -e OXYLABS_AI_STUDIO_API_KEY=<your-api-key> \
  -- uvx oxylabs-mcp

Claude Desktop

{
  "mcpServers": {
    "oxylabs": {
      "command": "uvx",
      "args": ["oxylabs-mcp"],
      "env": {
        "OXYLABS_USERNAME": "<username>",
        "OXYLABS_PASSWORD": "<password>"
      }
    }
  }
}

Configure only one credential set — enabling both exposes redundant tools.

Requirements

Oxylabs account with Web Scraper API or AI Studio access.
Python with uvx (from uv).
An MCP client (Claude Code or Claude Desktop).

Security

Scraping is proxied through Oxylabs — your IP is not exposed.
Review scraping targets for compliance with their terms of service.
Keep API credentials in the MCP config env; do not commit them.

Source Verification Notes

Verified on 2026-06-18:

Official repository oxylabs/oxylabs-mcp (MIT) documents the uvx oxylabs-mcp install, the OXYLABS_USERNAME/OXYLABS_PASSWORD and OXYLABS_AI_STUDIO_API_KEY credential sets, all eight tools including universal_scraper, google_search_scraper, amazon_search_scraper, amazon_product_scraper, ai_scraper, ai_crawler, ai_browser_agent, and ai_search.
Claude Code MCP documentation at code.claude.com/docs/en/mcp describes the stdio connector pattern used above.

#oxylabs #web-scraping #data-extraction #serp #ecommerce #automation

Source citations

Add this badge to your README

Show that Oxylabs MCP Server for Claude is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

[![Listed on HeyClaude](https://heyclau.de/badge/mcp/oxylabs-mcp-server.svg)](https://heyclau.de/entry/mcp/oxylabs-mcp-server)

How it compares

Oxylabs MCP Server for Claude side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.

Field	Oxylabs MCP Server for Claude Scrape any website, extract structured data, and search Google and Amazon from Claude — with the official Oxylabs MCP server providing universal web scraping with JS rendering, CAPTCHA bypass, AI-powered data extraction, and AI browser automation in one tool. Open dossier	WebClaw MCP Server Local-first MCP server for web scraping, crawling, URL mapping, batch extraction, structured extraction, summarization, diffing, brand extraction, and optional hosted API fallback for bot-protected pages. Open dossier	AgentQL MCP Server AgentQL MCP server for extracting structured JSON from public webpages using a URL and natural-language extraction prompt. Open dossier	Android Skills MCP Server for Claude Access AI-optimized Android development guides from Claude — search and retrieve SKILL.md content covering Jetpack Compose, Navigation 3, CameraX, AGP 9, App Functions, Edge-to-Edge, Android Profilers, XR, Google Play, and the Android CLI — with the Android Skills MCP server. Open dossier
Trust
Install risk	Review first	Review first	Review first	Review first
Notes	Safety ✓ Privacy ✓	Safety ✓ Privacy ✓	Safety ✓ Privacy ✓	Safety ✓ Privacy ✓
Category	mcp	mcp	mcp	mcp
Source	source-backed	source-backed	source-backed	source-backed
Author	Oxylabs	WebClaw	AgentQL	Jaewoong Eum (skydoves)
Added	2026-06-18	2026-06-06	2026-06-06	2026-06-18
Platforms	Claude CodeCodexCursorClaude Desktop	Claude CodeClaude Desktop	Claude CodeClaude Desktop	Claude CodeClaude Desktop
Source repo	—	—	—	—
Safety notes	✓All scraping requests are proxied through Oxylabs infrastructure — your real IP is never exposed to target sites. AI browser agent and AI crawler tools issue real web requests against target domains; ensure scraping complies with target site terms of service.	✓WebClaw MCP Server can scrape one URL, crawl same-origin links, map URLs, batch multiple URLs, extract structured data, summarize pages, compare snapshots, and extract brand metadata. Scraping, crawling, search, research, and hosted fallback can trigger target-site rate limits, bot protections, legal restrictions, or terms-of-service limits. The server validates public HTTP URLs and rejects private or internal destinations, but operators should still avoid fetching internal, secret, customer-specific, or credential-bearing URLs. Cookie-bearing requests, proxies, and browser profiles can expose authenticated sessions or route traffic through external infrastructure. Setting `WEBCLAW_API_KEY` enables hosted API fallback, which can send target URLs and page context to the WebClaw service. Structured extraction and summarization may use configured LLM providers; review provider data handling before enabling those tools with sensitive pages.	✓AgentQL MCP exposes one tool, `extract-web-data`, that sends a target URL and natural-language extraction prompt to the AgentQL API. The tool is intended for public webpages; do not use it to bypass access controls, scrape private pages, evade paywalls, or extract data where automated collection is prohibited. Web extraction can still trigger target-site rate limits, legal restrictions, robots guidance, or terms-of-service concerns. The source implementation uses AgentQL's query-data endpoint with fast mode, no screenshot capture, no scroll-to-bottom behavior, and no local browser cookies. Treat extracted output as untrusted web data that may include errors, stale content, ads, tracking text, or prompt-injection attempts.	✓The server runs entirely offline — no network requests are made during queries. All skill content is bundled with the npm package.
Privacy notes	✓Page content scraped from target sites is returned in Claude's context — treat sensitive competitor data or personal data in scraped results accordingly. Your `OXYLABS_USERNAME` and `OXYLABS_PASSWORD` authenticate to the Oxylabs Web Scraper API — keep them in the MCP config env.	✓URLs, fetched page content, crawl results, extracted structured data, snapshots, brand metadata, cookies, proxy settings, API keys, and LLM prompts can be exposed to the MCP client. Crawled pages may include personal data, customer content, non-public links, access tokens embedded in URLs, or site-specific identifiers. Diff snapshots and exported JSON can preserve page content longer than expected; store and delete them according to the workflow's retention needs. Hosted fallback, proxy providers, search/research APIs, and LLM providers may observe target URLs, headers, cookies, prompts, and extracted content when enabled. Redact sensitive URLs and extracted data before sharing MCP transcripts, crawl results, logs, or generated RAG context.	✓Target URLs, extraction prompts, API key-authenticated requests, and extracted structured data are sent to AgentQL's API. Extracted data can include personal data, copyrighted content, customer information, job postings, prices, social content, or other third-party material. AGENTQL_API_KEY should stay out of prompts, issues, logs, screenshots, and committed configuration files. Claude transcripts and downstream reports may retain extracted data, so avoid collecting information that is not approved for the model session.	✓No API keys, user data, or query content is sent to any external service. All lookups happen locally against the bundled skill snapshot.
Prerequisites	An Oxylabs account with Web Scraper API access — sign up at oxylabs.io. Web Scraper API username and password from your Oxylabs dashboard. Python with `uvx` available. An MCP client such as Claude Code or Claude Desktop.	Node.js for the `create-webclaw` installer, or Rust/Cargo when building the MCP binary from source. Review of AGPL-3.0 obligations before redistributing or operating modified server versions. Review of target-site terms, robots expectations, rate limits, and scraping permissions. Optional `WEBCLAW_API_KEY` only when hosted API fallback is acceptable for bot-protected or JavaScript-heavy pages.	Node.js and npx available to the MCP client runtime. AgentQL API key from the AgentQL developer portal. Approved list of public webpages or domains Claude may query. Review of target site terms, robots guidance, rate limits, and data-use rules before extraction.	Node.js with `npx` available. An MCP client such as Claude Code or Claude Desktop.
Install	`claude mcp add oxylabs -e OXYLABS_USERNAME=<username> -e OXYLABS_PASSWORD=<password> -- uvx oxylabs-mcp`	`npx create-webclaw`	`npx -y agentql-mcp`	`claude mcp add android-skills -- npx -y android-skills-mcp`
Config	`{ "mcpServers": { "oxylabs": { "command": "uvx", "args": ["oxylabs-mcp"], "env": { "OXYLABS_USERNAME": "<username>", "OXYLABS_PASSWORD": "<password>" } } } }`	`Manual-only setup: npx create-webclaw`	`{ "mcpServers": { "agentql": { "command": "npx", "args": ["-y", "agentql-mcp"], "env": { "AGENTQL_API_KEY": "<your-agentql-api-key>" } } } }`	`{ "mcpServers": { "android-skills": { "command": "npx", "args": ["-y", "android-skills-mcp"] } } }`
Citations	Source repositorygithub.com 2026-06-18T09:01:14+00:00 Documentationraw.githubusercontent.com Websiteoxylabs.io	Source repositorygithub.com 2026-06-18T09:01:14+00:00 Documentationraw.githubusercontent.com Submitted by oktofeesh12026-06-06	Source repositorygithub.com 2026-06-18T09:01:14+00:00 Documentationgithub.com Submitted by oktofeesh12026-06-06	Source repositorygithub.com 2026-06-18T09:01:14+00:00 Documentationraw.githubusercontent.com
Claim	Unclaimed	Unclaimed	Unclaimed	Unclaimed

Featured in

Best list: MCP servers for browser automation

Signals

Loading live community signals…

Safety notes

Privacy notes

Prerequisites

Schema details

About this resource

Overview

Key capabilities

Tools

How it compares

Installation

Claude Code (Web Scraper API)

Claude Code (AI Studio)

Claude Desktop

Requirements

Security

Source Verification Notes

Source citations

Add this badge to your README

How it compares

Related resources

WebClaw MCP Server

AgentQL MCP Server

Android Skills MCP Server for Claude

DataHub MCP Server for Claude

Featured in

Signals