Web, Search & Scraping MCP Servers for OpenAI Agents SDK

Per-call data for agents: graded behavioural science, dark-pattern detection, web fetch, geocode.

Fetch transcripts, subtitles, chapters, metadata and frames from YouTube and 10+ video platforms

Scrape and crawl websites into queryable tables: products, leads, Shopify catalogs, real estate.

Wayback Machine for agents: closest archived copy of a URL with its text, and full capture history

Search and read public Vigil pages with source URLs.

Create, read and monitor Wachete website-change wachets for a signed-in user.

Paid web, news, company, product, and geographic search plus clean page reading for agents.

The most accurate web access API. Stop getting blocked.

Fetch web pages with SSRF protection. Returns clean, readable markdown from any URL.

10 pay-per-call web tools: markdown, CSS scrape, links, crawl, screenshot, PDF, browser.

Extract clean markdown from any URL. Removes boilerplate. For RAG pipelines. x402.

Scrape, crawl, map and extract the web. Pay per call in USDC, no account or API key.

AI-native web scraper: scrape, crawl and map any site to clean markdown over stdio. MIT-licensed.

Business website planning and launch assistance with human-confirmed next steps.

Search global news in natural language. Filter by language, country, date, sentiment, and domain.

WhoisXML MCP — wraps WhoisXML API (whoisxmlapi.com)

Research proxy providers, compare published prices, and discover provider MCP integrations.

Fetch and extract data from any public web page, even JS-rendered or anti-bot protected

X-Correlation-Id charset, value discarded

Autonomous HTTP 402 Web Scraping Mesh on Base for $0.02 USDC.

Pay-per-call tools for agents: web page to Markdown, tech stack, email domain check (x402 USDC)