Web Search & Scraping MCP Servers
Search, news retrieval, crawling, scraping, extraction, and public web collection.
Earth Search
Published by GitHub account pipeworx-io
Searches the Earth Search STAC catalogue of Sentinel, Landsat, NAIP and Copernicus DEM imagery by area and date, returning item ids, footprints, cloud cover…
Dpla
Published by GitHub account pipeworx-io
Searches the Digital Public Library of America's ~50 million digitised items and returns full records and named collections.
Data Strasbourg
Published by GitHub account pipeworx-io
Searches, inspects and queries Strasbourg open data datasets through the Pipeworx gateway, with a router that reaches a much larger data catalog.
Data Odre
Published by GitHub account pipeworx-io
Pipeworx pack for ODRE French energy open data: search datasets, read schemas and run ODSQL queries on electricity and gas records.
Data Occitanie
Published by GitHub account pipeworx-io
Pipeworx pack for Occitanie Region open data: search datasets, inspect schemas and query records with ODSQL, plus gateway meta-tools.
Data Newcaledonia
Published by GitHub account pipeworx-io
Searches, inspects and queries New Caledonia open government datasets (data.gouv.nc) through the Pipeworx gateway, with ODSQL filtering and aggregation.
Data Loireatlantique
Published by GitHub account pipeworx-io
Searches, inspects and queries Loire-Atlantique open data datasets (OpenDataSoft) through the Pipeworx gateway, with a router to a much larger data catalog.
Data Angers
Published by GitHub account pipeworx-io
Pipeworx pack for Angers Loire Métropole open data (data.angers.fr), letting an assistant search datasets, read schemas and query records with ODSQL.
Crtsh
Published by GitHub account pipeworx-io
Searches public Certificate Transparency logs via crt.sh to list every TLS certificate and hostname issued for a domain, plus a gateway router to other data…
Corporate Satire
Published by GitHub account pipeworx-io
A joke generator that turns a plain announcement into a fabricated, satirical corporate press release, delivered through the Pipeworx gateway.
Copernicus Cds
Published by GitHub account pipeworx-io
Pipeworx pack for the Copernicus Climate Data Store: browse ~140 climate datasets and submit retrieval jobs for ERA5, CMIP6 and similar data.
Commoncrawl
Published by GitHub account pipeworx-io
Pipeworx pack for Common Crawl's public web archive: list crawl collections, search the CDX index for a URL, and read back archived page bytes.
Chrome Ux Report
Published by GitHub account pipeworx-io
Pipeworx pack exposing Google's Chrome UX Report so an assistant can pull real-user Core Web Vitals for a site or page, with history.
Businesswire
Published by GitHub account pipeworx-io
Pipeworx gateway connection scoped to Business Wire press releases, letting an assistant list, search and read recent wire releases, plus route other data…
Arcgis Sumter
Published by GitHub account pipeworx-io
Searches and queries City of Sumter, South Carolina open GIS data (parcels, zoning, city services) through ArcGIS services, with a gateway router for other…
511 Sf Bay
Published by GitHub account pipeworx-io
Pipeworx pack giving an assistant live Bay Area 511 transit data: operator codes, stop departure predictions, vehicle positions and service alerts.
Al Jazeera 360
Published by GitHub account ahmedaminsa
Lets an assistant search and browse Al Jazeera 360's Arabic shows, documentaries, podcasts and series, returning metadata and direct watch links.
Bandcamp crate digging
Published by GitHub account Venut-Technologies
Local MCP server that lets an assistant search Bandcamp and read public artist, label, album and track pages, including tracklists and prices.
AxenomIA AX-SCI-001 — Scientific Novelty & Evidence
Published by GitHub account Perlita2013
Remote MCP server that lets an assistant gather source-linked scientific evidence for a research question and read the agent's scope and human-review rules.
Genesis402 by UnyKorn (x402 pay-per-call)
Published by GitHub account FTHTrading
Genesis402 gives an assistant pay-per-call access to 360+ x402 endpoints for sanctions screening, company lookup, crypto risk, web and domain checks, and AI and
Dinogame
gg.dinogameOfficial publisher
Lets an assistant search dinogame.gg's catalogue of free browser games and its blog of Chrome Dino and gaming guides, returning play and citation links.
Pagemd
dev.kanekyOfficial publisher
Pagmd is a remote MCP server that fetches a public web page and returns its main content as clean Markdown with metadata, billed per call.
SnoopScan
com.snoopscanOfficial publisher
SnoopScan is a hosted web-scraping MCP server that turns public pages into markdown, JSON or schema-defined data for an AI assistant.
Saylor Innovations: pay-per-call data
com.saylorinnovationsOfficial publisher
A pay-per-call catalog of data endpoints an assistant can search, price and buy with x402 crypto payments, covering crypto, finance, research, law and public US