Web, Search & Scraping MCP Servers for OpenAI Agents SDK

Multi-provider proxy infrastructure for AI/ML. Geo, sessions, cost-aware routing, usage tools.

Tiny Tiny RSS MCP Server - read and write tt-rss feeds via an AI assistant.

MCP server for web scraping and converting web pages to Markdown with Playwright support

Web page change tracking with structured diffs. markgrab + snapgrab integration.

MCP web extraction for permitted public pages: no-key demo plus live URL-to-JSON and Markdown output with honest blocked-page errors

IP Geolocation MCP server that query the geolocation information using IP2Location.io API.

MCP server for pordl — read open-content web sources (public-domain, Creative Commons, permissive OSS docs) as clean markdown.

SERPHouse MCP Server — connect AI assistants to live SERP data, Google verticals, and SEO intelligence.

Adaptive web research for AI coding agents — 91% of Deep Research quality at 5% cost

Query webpages and extract structured data using natural language

MCP server that runs Google AI Mode searches via a browser sidecar extension using your own logged-in session.

Unified search across DuckDuckGo, GitHub, npm, PyPI, Stack Overflow, Wikipedia and Hacker News — for AI agents. No API keys required. Part

Give your AI agent the ability to extract clean, structured data from any web page. Articles, products, metadata, tables, contact info

Official MCP server for DataBlue web scraping and structured data APIs

Enhanced web search and content extraction MCP - search engines, RSS, YouTube transcripts, metadata extraction

WHOIS domain MCP server that query the WHOIS information using IP2WHOIS API.

- This is an MCP wrapper to jocmp/mercury-parser: A maintained fork of Postlight Parser

5 years of corroborated news events, queryable from your shell — the CLI for newsflash.sh, breaking news wired for agents.

MCP server for web search that extracts relevant excerpts instead of summarizing. BM25 + heuristic ranking, no LLM needed.

A Model Context Protocol server for Scrapezy

Scrape webpages, handle JavaScript and CAPTCHA, extract structured data