The missing link between AI models and the real‑world web: one API that delivers clean, structured data from any site.
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.
Oxylabs MCP provides two sets of tools that can be used together or independently:
- universal_scraper: Uses Oxylabs Web Scraper API for general website scraping;
- google_search_scraper: Uses Oxylabs Web Scraper API to extract results from Google Search;
- amazon_search_scraper: Uses Oxylabs Web Scraper API to scrape Amazon search result pages;
- amazon_product_scraper: Uses Oxylabs Web Scraper API to extract data from individual Amazon product pages.
- ai_scraper: Scrape content from any URL in JSON or Markdown format with AI-powered data extraction;
- ai_crawler: Based on a prompt, crawls a website and collects data in Markdown or JSON format across multiple pages;
- ai_browser_agent: Based on prompt, controls a browser and returns data in Markdown, JSON, HTML, or screenshot formats;
- ai_search: Search the web for URLs and their contents with AI-powered content extraction.
Before you begin, make sure you have at least one of the following:
- Oxylabs Web Scraper API Account: Obtain your username and password from Oxylabs (1-week free trial available);
- Oxylabs AI Studio API Key: Obtain your API key from Oxylabs AI Studio. (1000 credits free).
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 |
Based on provided credentials, the server will automatically expose the corresponding tools:
- If only
OXYLABS_USERNAME
andOXYLABS_PASSWORD
are provided, the server will expose the Web Scraper API tools; - If only
OXYLABS_AI_STUDIO_API_KEY
is provided, the server will expose the AI Studio tools; - If both
OXYLABS_USERNAME
andOXYLABS_PASSWORD
andOXYLABS_AI_STUDIO_API_KEY
are provided, the server will expose all tools.
❗❗❗ Important note: if you don't have Web Scraper API or Oxylabs AI studio credentials, delete the corresponding environment variables placeholders. Leaving placeholder values will result in exposed tools that do not work.
- Install the uvx package manager:
OR:
# 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"
- Use the following config:
{ "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" } } } }
-
Install the uv package manager:
# macOS and Linux curl -LsSf https://astral.sh/uv/install.sh | sh
OR:
# Windows powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
-
Use the following config:
{ "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" } } } }
- Go to https://smithery.ai/server/@oxylabs/oxylabs-mcp;
- Login with GitHub or Google;
- Find the Connect section;
- Follow the instructions to generate the config or auto install command.
Navigate to Claude → Settings → Developer → Edit Config and add one of the configurations above to the claude_desktop_config.json
file.
Navigate to Cursor → Settings → Cursor Settings → MCP. Click Add new global MCP server and add one of the configurations above.
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"
}
}
Distributed under the MIT License – see LICENSE for details.
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.
Scrape content from any site
- Extract data from any URL, including complex single-page applications
- Fully render dynamic websites using headless browser support
- Choose full JavaScript rendering, HTML-only, or none
- Emulate Mobile and Desktop viewports for realistic rendering
Automatically get AI-ready data
- Automatically clean and convert HTML to Markdown for improved readability
- Use automated parsers for popular targets like Google, Amazon, and more
Bypass blocks & geo-restrictions
- Bypass sophisticated bot protection systems with high success rate
- Reliably scrape even the most complex websites
- Get automatically rotating IPs from a proxy pool covering 195+ countries
Flexible setup & cross-platform support
- Set rendering and parsing options if needed
- Feed data directly into AI models or analytics tools
- Works on macOS, Windows, and Linux
Built-in error handling and request management
- Comprehensive error handling and reporting
- Smart rate limiting and request management
Imagine telling your LLM "Summarise the latest Hacker News discussion about GPT‑5" – 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 |