What credentials do I need to use the server?
You need at least one of: an Oxylabs Web Scraper API username/password or an Oxylabs AI Studio API key. The server exposes corresponding tools based on the credentials provided.
@oxylabs
基本情報
Official Oxylabs MCP integration
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"oxylabs_scraper_uvx": {
"command": "uvx",
"args": [
"oxylabs-mcp"
],
"env": {
"OXYLABS_USERNAME": "OXYLABS_USERNAME",
"OXYLABS_PASSWORD": "OXYLABS_PASSWORD"
}
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。
The Oxylabs MCP Server bridges AI models and the web, enabling them to scrape any URL, render JavaScript-heavy pages, extract and format content for AI use, manage CAPTCHA, and access geo-restricted web data from over 195 countries.
Configure via uvx, uv, or Smithery by setting environment variables (OXYLABS_USERNAME, OXYLABS_PASSWORD, OXYLABS_AI_STUDIO_API_KEY). The server automatically exposes Web Scraper API tools, AI Studio tools, or both depending on which credentials are provided. Manual setup in Claude Desktop or Cursor AI is supported.
You need at least one of: an Oxylabs Web Scraper API username/password or an Oxylabs AI Studio API key. The server exposes corresponding tools based on the credentials provided.
Set the environment variables `OXYLABS_USERNAME`, `OXYLABS_PASSWORD`, and/or `OXYLABS_AI_STUDIO_API_KEY` in your MCP client config. If using Smithery, you can authenticate via OAuth2 or pass credentials as query parameters.
The server can be run via `uvx` (recommended) or `uv` on macOS, Windows, or Linux. No additional runtime beyond Python and the package manager is needed.
Data is retrieved from Oxylabs’ Web Scraper API or AI Studio APIs and returned directly to the LLM client. It is not stored or processed by the server itself after the response is sent.
Yes, it uses Oxylabs’ global proxy network to manage automated request walls, CAPTCHAs, and IP rotation from a proxy pool covering 195+ countries.

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
A search tool helps dev to solve the naming things problem.
MCP Toolbox for Databases is an open source MCP server for databases.
PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct
不止于 CSS
コメント