Oxylabs Oxylabs MCP server
{
"mcpServers": {
"smithery-oxylabs-oxylabs": {
"type": "http",
"url": "https://server.smithery.ai/@oxylabs/oxylabs-mcp/mcp"
}
}
}{
"mcpServers": {
"smithery-oxylabs-oxylabs": {
"type": "http",
"url": "https://server.smithery.ai/@oxylabs/oxylabs-mcp/mcp"
}
}
}{
"mcpServers": {
"smithery-oxylabs-oxylabs": {
"type": "http",
"url": "https://server.smithery.ai/@oxylabs/oxylabs-mcp/mcp"
}
}
}{
"servers": {
"smithery-oxylabs-oxylabs": {
"type": "http",
"url": "https://server.smithery.ai/@oxylabs/oxylabs-mcp/mcp"
}
}
}{
"mcpServers": {
"smithery-oxylabs-oxylabs": {
"type": "http",
"url": "https://server.smithery.ai/@oxylabs/oxylabs-mcp/mcp"
}
}
}file .mcp.json (in your project root)file claude_desktop_config.jsonfile ~/.cursor/mcp.jsonfile .vscode/mcp.jsonfile ~/.codeium/windsurf/mcp_config.jsonversion 1.13.1
What it does
This MCP server connects AI models to web data by providing scraping, crawling, and browser automation tools via the Oxylabs API. It supports both the Web Scraper API (for URL scraping, Google/Amazon searches) and the AI Studio API (for intelligent extraction, crawling, and browser control).
- Scrape content from any URL with JavaScript rendering, geo-targeting, and formatted output (Markdown, HTML, or links).
- Extract structured data from search results or product pages using AI-powered extraction with customizable schemas.
- Automate browser interactions like navigation, form filling, and clicking based on natural language instructions.
Tools this server exposes
| Tool | Does |
|---|---|
| universal_scraper | Scrapes any URL with optional JavaScript rendering, geo-targeting, and output as Markdown, HTML, or links. |
| google_search_scraper | Extracts results from Google Search with optional parsing into structured JSON. |
| amazon_search_scraper | Scrapes Amazon search result pages with optional parsing into structured JSON. |
| amazon_product_scraper | Extracts data from individual Amazon product pages. |
| ai_scraper | Scrapes content from any URL with AI-powered extraction, returning JSON, CSV, Markdown, or TOON format. |
| ai_crawler | Crawls a website from a starting URL based on a prompt and collects data across multiple pages. |
| ai_browser_agent | Controls a real browser based on a prompt to navigate, click, fill forms, and return results. |
| ai_search | Searches the web and optionally returns Markdown content of each result. |
| ai_map | Maps a website's URLs, filtered by keywords or a prompt. |
| generate_schema | Generates an OpenAPI-format JSON schema for structured extraction with the AI tools. |
Before you enable it
An MCP server runs with whatever access you give it. Start with a development account rather than production, and check which tools the server exposes before you let an agent call them unattended.