Web, Search & Scraping MCP Servers for Codex CLI

YouTube transcripts, open jobs from careers pages, app store reviews and X posts for AI agents.

Zero-signup anonymous link-unfurl API. One GET returns clean JSON metadata for any public URL.

Origin scheme+host shape, URL discarded

Read any public web page as clean Markdown for LLMs, with its metadata. Paid per call, x402.

Telegram/VK audience scraping, marketplaces, Russian government registers. Free open dataset.

Apify MCP — run web-scraping Actors and fetch their dataset results.

Crawlbase MCP — wraps the Crawlbase Crawling API (crawlbase.com, formerly

Currents MCP — wraps the Currents API (currentsapi.services)

Decodo MCP — wraps the Decodo Web Scraping API (decodo.com, formerly

Diffbot MCP — Knowledge Graph company enrichment + web content extraction (diffbot.com)

Education Feeds MCP.

Entertainment Feeds MCP.

Live Feeds (RSS/Atom) MCP.

Finance Feeds MCP.

Hacker News MCP — search and retrieve stories from Hacker News

Jina AI Reader/Search MCP — turn any URL into clean LLM-ready markdown, plus web search.

Microlink MCP — wraps Microlink API (free tier, no auth required)

Live news search: recent stories in 45 languages, grouped by coverage and checked for relevance.

Extract product names, prices, and currency from any e-commerce product page in one call.

Read pages & files to text, news, weather, market holidays and timezones via x402.

Google Jobs listings with parsed salaries and direct apply links, more than 10 per search.