Web Search & Scraping MCP Servers
Search, news retrieval, crawling, scraping, extraction, and public web collection.
anymd
Published by GitHub account SylphxAI
Local MCP server that converts PDF, Office, EPUB, HTML, image and media files into clean Markdown an assistant can read, outline and search.
Shopee MCP (via SEA MCP)
Published by GitHub account SeaMCP
Remote MCP server that lets an assistant search Shopee shops, listings and categories across eight Shopee markets for market and seller research.
ProofGraph (Antigravity MCP)
Published by GitHub account AI-BuildInfra
Local MCP server that gives an AI agent an evidence-first entity and knowledge graph for verifying claims and tracing provenance.
URLpipe
dev.urlpipeOfficial publisher
Hosted URLpipe server that renders public pages in real Chrome so an assistant can read them as Markdown, screenshots, PDFs, metadata or custom data.
New Runtime public records
com.newruntimeOfficial publisher
Remote New Runtime archive of AI-engineering news and analysis that an assistant can search, read, and contextualize by URL.
Hook Detector
com.hookdetectorOfficial publisher
Finds real TikTok, Instagram and YouTube hooks on a topic, keeps or rejects them, and rewrites them for your niche, using a paid credit account.
US Codex
org.uscodexOfficial publisher
Remote MCP server for US federal law: search, read, cross-reference and compare the US Code, CFR, public laws, bills and executive orders.
PJELLY Deals
io.peanutbutterjellyOfficial publisher
A remote MCP server that lets an assistant search, compare and look up crypto exchange and hardware wallet offers from PeanutButterJelly.io's buying guides.
Swiss Grounding
Published by GitHub account soheil1lotfi
A read-only MCP server that answers questions about Switzerland from official federal, cantonal and municipal sources and cites the responsible authority.
Worldpop
Published by GitHub account pipeworx-io
WorldPop pack that estimates how many people live inside any GeoJSON polygon using 100 m gridded population data for 2000-2020.
Us National Archives
Published by GitHub account pipeworx-io
Searches the US National Archives Catalog (NARA) for federal records and returns record details and digitized page images.
Uk Tribunals
Published by GitHub account pipeworx-io
Searches and reads UK first-tier and Upper Tribunal decisions published on GOV.UK, with a gateway router for other data sources.
Trimet
Published by GitHub account pipeworx-io
Pipeworx Trimet gives an assistant live Portland-area transit data: arrivals, nearby stops, vehicle positions and service alerts.
Tga Artg
Published by GitHub account pipeworx-io
Searches Australia's TGA ARTG register of approved medicines, biologicals and medical devices, with full entry records and PI/CMI links.
Taiwan Companies
Published by GitHub account pipeworx-io
Searches Taiwan's statutory company register by name or 統一編號 and returns registration records, capital and legal standing.
Stats Nz
Published by GitHub account pipeworx-io
Searches New Zealand official statistics from Stats NZ's Aotearoa Data Explorer and pulls dataset observations, dimensions and code lists.
Scotcourts
Published by GitHub account pipeworx-io
Searches Scottish Courts and Tribunals Service judgments from 1999 onward and resolves judgment PDF links, via the Pipeworx gateway.
Reliefweb
Published by GitHub account pipeworx-io
Pipeworx gateway endpoint for UN OCHA ReliefWeb: lets an assistant search humanitarian reports, disasters and full report text, plus route other data questions.
Regon Pl
Published by GitHub account pipeworx-io
Looks up Polish companies in the official REGON/BIR1.1 register by NIP, REGON or KRS number and returns name, address and entity type.
Pulse Verity
Published by GitHub account pipeworx-io
Pipeworx adapter for the Pulse Verity crypto index: signed, verifiable price prints plus a gateway router to 1,800+ other data sources.
Prweb
Published by GitHub account pipeworx-io
Pipeworx PRWeb server that lets an assistant read, search and fetch live PRWeb press releases, plus route other data questions through the wider Pipeworx…
Prnewswire
Published by GitHub account pipeworx-io
Pipeworx PR Newswire connector that lets an assistant read, search and fetch the newest press releases from PR Newswire's rolling all-releases feed.
Planetary Computer
Published by GitHub account pipeworx-io
Searches Microsoft's Planetary Computer satellite and environmental imagery catalogue, returning collection metadata, scene footprints, dates and asset URLs.
Ofr Funding
Published by GitHub account pipeworx-io
OFR Short-Term Funding Monitor API — data.financialresearch.gov/v1, keyless, no auth wall. The…