Oxylabs MCP Server

The missing link between AI models and the real‑world web: one API that delivers clean, structured data from any site.

📖 Overview

The Oxylabs MCP server provides a bridge between AI models and the web. It enables them to scrape any URL, render JavaScript-heavy pages, extract and format content for AI use, bypass anti-scraping measures, and access geo-restricted web data from 195+ countries.

This implementation leverages the Model Context Protocol (MCP) to create a secure, standardized way for AI assistants to interact with web content.

Why Oxylabs MCP?  🕸️ ➜ 📦 ➜ 🤖

Imagine telling your LLM "Summarise the latest Hacker News discussion about GPT‑7" – and it simply answers.
MCP (Multi‑Client Proxy) makes that happen by doing the boring parts for you:

| What Oxylabs MCP does | Why it matters to you | |-------------------------------------------------------------------|------------------------------------------| | Bypasses anti‑bot walls with the Oxylabs global proxy network | Keeps you unblocked and anonymous | | Renders JavaScript in headless Chrome | Single‑page apps, sorted | | Cleans HTML → JSON | Drop straight into vector DBs or prompts | | Optional structured parsers (Google, Amazon, etc.) | One‑line access to popular targets |

✨ Key Features

🛠️ MCP Tools

Oxylabs MCP provides two sets of tools that can be used together or independently:

Oxylabs Web Scraper API Tools

1. universal_scraper: Uses Oxylabs Web Scraper API for general website scraping.
2. google_search_scraper: Uses Oxylabs Web Scraper API to extract results from Google Search.
3. amazon_search_scraper: Uses Oxylabs Web Scraper API to scrape Amazon search result pages.
4. amazon_product_scraper: Uses Oxylabs Web Scraper API to extract data from individual Amazon product pages.

Oxylabs AI Studio Tools

The Oxylabs AI Studio MCP server provides various AI tools for your agents:

5. ai_scraper: Scrape content from any URL in JSON or Markdown format with AI-powered data extraction.
6. ai_crawler: Based on a prompt, crawls a website and collects data in Markdown or JSON format across multiple pages.
7. ai_browser_agent: Given a task, the agent controls a browser to achieve the given objective and returns data in Markdown, JSON, HTML, or screenshot formats.
8. ai_search: Search the web for URLs and their contents with AI-powered content extraction.

💡 Example Queries

When you've set up the MCP server with Claude, you can make requests like:

Web Scraper API Examples

• Could you scrape https://www.google.com/search?q=ai page?
• Scrape https://www.amazon.de/-/en/Smartphone-Contract-Function-Manufacturer-Exclusive/dp/B0CNKD651V with parse enabled
• Scrape https://www.amazon.de/-/en/gp/bestsellers/beauty/ref=zg_bs_nav_beauty_0 with parse and render enabled
• Use web unblocker with render to scrape https://www.bestbuy.com/site/top-deals/all-electronics-on-sale/pcmcat1674241939957.c

AI Studio Examples

• Use AI scraper to get top news headlines from https://news-site.com in JSON format.
• Use AI crawler with prompt "extract all product information" to crawl https://example-store.com
• Use browser agent with task "log in and extract dashboard data" on https://complex-app.com
• Use AI search to find 5 "latest AI developments" and return URLs with their content

✅ Prerequisites

Before you begin, make sure you have:

• Oxylabs Web Scraper API Account: Obtain your username and password from Oxylabs (1-week free trial available)
• Oxylabs AI Studio API Key (Optional): For AI-powered tools, obtain your API key from Oxylabs AI Studio (separate service)

Basic Usage

Via Smithery CLI:

• Node.js (v16+)
• npx command-line tool

Via uv:

• uv package manager – install it using this guide

Local/Dev Setup

• Python 3.12+
• uv package manager – install it using this guide

🧩 API Parameters

The Oxylabs MCP Universal Scraper accepts these parameters:

| Parameter | Description | Values | |-------------------|-------------------------------------------------|---------------------------| | url | The URL to scrape | Any valid URL | | render | Use headless browser rendering | html or None | | geo_location | Sets the proxy's geo location to retrieve data. | Brasil, Canada, etc. | | user_agent_type | Device type and browser | desktop, tablet, etc. | | output_format | The format of the output | links, md, html |

🔧 Configuration

# example for Claude Desktop
npx -y @smithery/cli@latest install @upstash/context7-mcp --client claude --key <smithery_key>

# macOS and Linux
curl -LsSf https://astral.sh/uv/install.sh | sh

# Windows
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

{
  "mcpServers": {
    "oxylabs": {
      "command": "uvx",
      "args": ["oxylabs-mcp"],
      "env": {
        "OXYLABS_USERNAME": "OXYLABS_USERNAME",
        "OXYLABS_PASSWORD": "OXYLABS_PASSWORD",
        "OXYLABS_AI_STUDIO_API_KEY": "OXYLABS_AI_STUDIO_API_KEY"
      }
    }
  }
}

# macOS and Linux
curl -LsSf https://astral.sh/uv/install.sh | sh

# Windows
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

{
  "mcpServers": {
    "oxylabs": {
      "command": "uv",
      "args": [
        "--directory",
        "/<Absolute-path-to-folder>/oxylabs-mcp",
        "run",
        "oxylabs-mcp"
      ],
      "env": {
        "OXYLABS_USERNAME": "OXYLABS_USERNAME",
        "OXYLABS_PASSWORD": "OXYLABS_PASSWORD",
        "OXYLABS_AI_STUDIO_API_KEY": "OXYLABS_AI_STUDIO_API_KEY"
      }
    }
  }
}

Manual Setup with Claude Desktop

Navigate to Claude → Settings → Developer → Edit Config and add one of the configurations above to the claude_desktop_config.json file.

Manual Setup with Cursor AI

Navigate to Cursor → Settings → Cursor Settings → MCP. Click Add new global MCP server and add one of the configurations above.

⚙️ Environment variables

Oxylabs MCP server supports the following environment variables

| Name | Description | Default | |---------------------------|-----------------------------------------------|---------| | OXYLABS_USERNAME | Your Oxylabs Web Scraper API username | | | OXYLABS_PASSWORD | Your Oxylabs Web Scraper API password | | | OXYLABS_AI_STUDIO_API_KEY | Your Oxylabs AI Studio API key | | | LOG_LEVEL | Log level for the logs returned to the client | INFO |

*At least one set of credentials (Web Scraper API or AI Studio) is required to use the MCP server.

Credential Requirements

The Oxylabs MCP server supports two independent services:

• Oxylabs Web Scraper API: Requires OXYLABS_USERNAME and OXYLABS_PASSWORD
• Oxylabs AI Studio: Requires OXYLABS_AI_STUDIO_API_KEY

You can use either service independently or both together. The server will automatically detect which credentials are available and enable the corresponding tools.

📝 Logging

Server provides additional information about the tool calls in notification/message events

{
  "method": "notifications/message",
  "params": {
    "level": "info",
    "data": "Create job with params: {\"url\": \"https://ip.oxylabs.io\"}"
  }
}

{
  "method": "notifications/message",
  "params": {
    "level": "info",
    "data": "Job info: job_id=7333113830223918081 job_status=done"
  }
}

{
  "method": "notifications/message",
  "params": {
    "level": "error",
    "data": "Error: request to Oxylabs API failed"
  }
}

🛡️ License

Distributed under the MIT License – see LICENSE for details.

About Oxylabs

Established in 2015, Oxylabs is a market-leading web intelligence collection platform, driven by the highest business, ethics, and compliance standards, enabling companies worldwide to unlock data-driven insights.