Oxylabs MCP Server

MCPOfficialOpen SourceMIT59.0

by oxylabs • Analytics & Monitoring

A bridge between AI models and the web that scrapes any URL, renders JavaScript pages, extracts and cleans content, and bypasses anti‑scraping and geo‑restrictions.

Example Use Cases

1
Scrape and fully render JavaScript-heavy web pages to extract up-to-date content.
2
Cleaned, AI-ready outputs (Markdown or JSON) from arbitrary HTML for summarization, indexing, or ingestion into models.
3
Reliable access to geo-restricted or anti-bot protected sites using rotating proxies across many countries.

Description

Oxylabs MCP Server exposes tools that let agents scrape and render websites (including JS-heavy single‑page apps), convert HTML to AI‑ready JSON or Markdown, and use structured parsers for common targets like Google and Amazon. It integrates with Oxylabs Web Scraper API and Oxylabs AI Studio, supports headless browser rendering, automatic cleaning/parsing, and rotating proxy IPs across 195+ countries to bypass blocks and geo-restrictions. The server requires Oxylabs credentials (username/password or AI Studio API key) and will expose only the corresponding tools based on provided credentials.

Capabilities(10 total)

Tools (10)

ai_crawler

Tool useful for crawling a website from starting url and returning data in a specified format. Schema is required only if output_format is json, csv or toon. 'render_javascript' is used to render javascript heavy websites. 'return_sources_limit' is used to limit the number of sources to return, for example if you expect results from single source, you can set it to 1.

url:string*user_prompt:string*output_format:stringschema:anyrender_javascript:booleanreturn_sources_limit:integergeo_location:any

ai_scraper

Scrape the contents of the web page and return the data in the specified format. Schema is required only if output_format is json or csv. 'render_javascript' is used to render javascript heavy websites.

url:string*output_format:stringschema:anyrender_javascript:booleangeo_location:any

ai_browser_agent

Run the browser agent and return the data in the specified format. This tool is useful if you need navigate around the website and do some actions. It allows navigating to any url, clicking on links, filling forms, scrolling, etc. Finally it returns the data in the specified format. Schema is required only if output_format is json, csv or toon. 'task_prompt' describes what browser agent should achieve

url:string*task_prompt:string*output_format:stringschema:anygeo_location:any

ai_search

Search the web based on a provided query. 'return_content' is used to return markdown content for each search result. If 'return_content' is set to True, you don't need to use ai_scraper to get the content of the search results urls, because it is already included in the search results. if 'return_content' is set to True, prefer lower 'limit' to reduce payload size.

query:string*limit:integerrender_javascript:booleanreturn_content:booleangeo_location:any

generate_schema

Generate a json schema in openapi format.

user_prompt:string*app_name:string*

Quick Actions

View on GitHub

Security

Scanned 2 month(s) ago

Risk Level

MINIMAL

Read-only data retrieval, no side effects

Trust Score

C63/100

11/17 checks passed

Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.

Quick Stats

Service TypeMCP

Pricing ModelFreemium

Capabilities10 Tools / 0 Prompts / 0 Resources

Owneroxylabs

CategoryAnalytics & Monitoring

DependenciesStandalone

Set Your Username