Discover our GTM Flywheel: Content, Ads & Outbound working as oneLearn more
Skip to main content
MCP Server

Oxylabs MCP

Jun 21, 2026
About

Oxylabs MCP server scrapes any website, rendering JavaScript and bypassing anti-bot measures. It delivers clean, structured data ready for AI models from over 195 countries.

How to Use

How to Install and Use Oxylabs MCP

Oxylabs MCP is a tool that helps you get clean, structured data from any website. It works well with AI models by scraping web pages, rendering JavaScript, and bypassing blocks. Here’s a simple guide to install and start using it.

Step 1: Get Your Oxylabs Credentials

Before installing, you need to have access to Oxylabs services. You must have at least one of these:

  • Oxylabs Web Scraper API Account – Get your username and password from Oxylabs Dashboard. You can try it free for one week.
  • Oxylabs AI Studio API Key – Get your API key from Oxylabs AI Studio. You get 1000 free credits.

Make sure you have these ready because you will need them to configure the MCP server.

Step 2: Install Oxylabs MCP

You can install Oxylabs MCP on macOS, Linux, or Windows. The easiest way is to use the uv or uvx package managers.

Installing with uvx

First, install uvx:

  • On macOS or Linux, run this in your terminal:
curl -LsSf https://astral.sh/uv/install.sh | sh
  • On Windows, run this in PowerShell:
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

Then, create a config file with this content:

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

Replace "your_username", "your_password", and "your_api_key" with your actual credentials.

Installing with uv

If you prefer uv, install it the same way as uvx above. Then use this config:

{
  "mcpServers": {
    "oxylabs": {
      "command": "uv",
      "args": [
        "--directory",
        "/absolute/path/to/oxylabs-mcp",
        "run",
        "oxylabs-mcp"
      ],
      "env": {
        "OXYLABS_USERNAME": "your_username",
        "OXYLABS_PASSWORD": "your_password",
        "OXYLABS_AI_STUDIO_API_KEY": "your_api_key"
      }
    }
  }
}

Make sure to replace /absolute/path/to/oxylabs-mcp with the real folder path where you installed MCP.

Step 3: Configure Environment Variables

Oxylabs MCP uses environment variables to know your credentials. Here are the variables you can set:

  • 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 – (Optional) Set log detail level, default is INFO

Set only the variables you have credentials for. If you don’t have Web Scraper API or AI Studio keys, remove those variables to avoid errors.

Step 4: Run Oxylabs MCP Server

Once installed and configured, start the MCP server by running:

uvx oxylabs-mcp

or, if using uv:

uv --directory /absolute/path/to/oxylabs-mcp run oxylabs-mcp

The server will start and expose the tools based on your credentials.

Step 5: Use Oxylabs MCP Tools

Oxylabs MCP offers two main toolsets:

  • Web Scraper API Tools for scraping websites, Google, Amazon, and product pages.
  • AI Studio Tools for AI-powered scraping, crawling, browsing, and searching.

You can call these tools through the MCP API, and the server will handle rendering, scraping, and cleaning the data for you.


By following these steps, you will have Oxylabs MCP installed and ready to get clean, structured web data fast and easily.

Details

TypeMCP Server
UpdatedJun 21, 2026
CreatedMar 16, 2026
DocumentationView docs
View Documentation