Oxylabs AI Studio
AI-powered tools for web scraping, crawling, and browser automation.
Oxylabs AI Studio MCP Server
📖 Overview
The Oxylabs AI Studio MCP server provides various AI tools for your agents.:
- Scrape: Allows getting content from any url in json or markdown format.
- Crawl: Based on prompt crawls a website and collects data in markdown or json format.
- Browser Agent: Given a task, agent controls a browser to achieve given object and returns data in markdown, json, html or screenshot formats.
- Search: Allows search the web for urls and their contents.
✅ Prerequisites
Obtain your Api Key from Oxylabs AI Studio dashboard:
Basic Usage
**Python >=3.10+**To run the server best to use uv:
- install it using this guide
- To setup with cursor the easiest way is to use uvx.
cursor uvx
{ "mcpServers": { "oxylabs-ai-studio": { "command": "uvx", "args": ["oxylabs-ai-studio-mcp"], "env": { "OXYLABS_AI_STUDIO_API_KEY": "OXYLABS_AI_STUDIO_API_KEY" } } } }
You can also pull the project and run it locally with uv in cursor:
{ "mcpServers": { "oxylabs-ai-studio": { "command": "uv", "args": [ "--directory", "//oxylabs-ai-studio-mcp", "run", "oxylabs-ai-studio-mcp" ], "env": { "OXYLABS_AI_STUDIO_API_KEY": "OXYLABS_AI_STUDIO_API_KEY" } } } }
Agent example:
import os import asyncio
from pydantic_ai import Agent from pydantic_ai.mcp import MCPServerStdio
server = MCPServerStdio(
'uvx',
args=[
'oxylabs-ai-studio-mcp',
],
env={
"OXYLABS_AI_STUDIO_API_KEY": "<your_api_key>",
},
)
requires OPENAI_API_KEY to be set.
agent = Agent('openai:gpt-4o', mcp_servers=[server])
async def main():
async with agent.run_mcp_servers():
result = await agent.run('Got to oxylabs careers page and first first available job and return the job title and description.')
print(result.output)
if name == "main": asyncio.run(main())
Related Servers
MCP Web Research Server
A server for web research that brings real-time information into AI models and researches any topic.
Apify
Use 3,000+ pre-built cloud tools to extract data from websites, e-commerce, social media, search engines, maps, and more
MCP Chrome Server
A server for browser automation using Google Chrome, based on the MCP framework.
Playwright Server
A server providing Playwright tools for browser automation and web scraping.
Horse Racing News
Fetches horse racing news from the thoroughbreddailynews.com RSS feed.
Web-curl
Fetch, extract, and process web and API content. Supports resource blocking, authentication, and Google Custom Search.
Puppeteer
Browser automation using Puppeteer, with support for local, Docker, and Cloudflare Workers deployments.
Cloudflare Browser Rendering
Provides web context to LLMs using Cloudflare's Browser Rendering API.
Scrapezy
Extract structured data from websites using the Scrapezy API.
Firecrawl
Extract web data with Firecrawl