Catalog

Find the connector for your task

Explore by use, narrow your options, then check the server before configuring your assistant.

Research & knowledge ×Extract web pages ×

Extract web pages

150 results

instagram

com.jojapi

Instagram: Instagram public data scraper API for search, users, posts, hashtags, locations and more.

Extract web pagesPublish on social networksAuthentication not declared

Publisher details & categorization

https://mcp.jojapi.com/instagram

com.jojapi/instagram

Instagram: Instagram public data scraper API for search, users, posts, hashtags, locations and more.

Suggested from the publisher's metadata; capabilities have not been tested.

Matching terms : instagram, scraper

Decodo

io.github.pipeworx-io

Decodo MCP — wraps the Decodo Web Scraping API (decodo.com, formerly Smartproxy). Rotating…

Extract web pagesAuthentication not declared

Publisher details & categorization

https://gateway.pipeworx.io/decodo/mcp

io.github.pipeworx-io/decodo

Decodo MCP — wraps the Decodo Web Scraping API (decodo.com, formerly Smartproxy). Rotating…

Suggested from the publisher's metadata; capabilities have not been tested.

Matching terms : scraping

Oxylabs

io.github.pipeworx-io

Oxylabs MCP — Oxylabs Web Scraper API (oxylabs.io)

Extract web pagesAuthentication not declared

Publisher details & categorization

https://gateway.pipeworx.io/oxylabs/mcp

io.github.pipeworx-io/oxylabs

Oxylabs MCP — Oxylabs Web Scraper API (oxylabs.io)

Suggested from the publisher's metadata; capabilities have not been tested.

Matching terms : scraper

Scrapingant

io.github.pipeworx-io

ScrapingAnt MCP — wraps the ScrapingAnt web scraping API (scrapingant.com)

Extract web pagesAuthentication not declared

Publisher details & categorization

https://gateway.pipeworx.io/scrapingant/mcp

io.github.pipeworx-io/scrapingant

ScrapingAnt MCP — wraps the ScrapingAnt web scraping API (scrapingant.com)

Suggested from the publisher's metadata; capabilities have not been tested.

Matching terms : scraping

Scrapingbee

io.github.pipeworx-io

ScrapingBee MCP — wraps the ScrapingBee headless-scraping API (scrapingbee.com)

Extract web pagesAuthentication not declared

Publisher details & categorization

https://gateway.pipeworx.io/scrapingbee/mcp

io.github.pipeworx-io/scrapingbee

ScrapingBee MCP — wraps the ScrapingBee headless-scraping API (scrapingbee.com)

Suggested from the publisher's metadata; capabilities have not been tested.

Matching terms : scraping

Apify

io.github.pipeworx-io

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

Extract web pagesAccess datasetsAuthentication not declared

Publisher details & categorization

https://gateway.pipeworx.io/apify/mcp

io.github.pipeworx-io/apify

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

Suggested from the publisher's metadata; capabilities have not been tested.

Matching terms : dataset, scraping

Guided comparisons: web, documentation, PDFs, signatures

Search the web with an assistantSearch documentationRead or transform a PDFGet a document signed

How are uses assigned?

Every catalog entry is analyzed on import and update. Uses are inferred from names and publisher descriptions, not a certification. Several uses may apply. Insufficient descriptions stay in ‘To clarify’. Authentication not declared does not mean free or unauthenticated access.

16,544 entries with a suggested use · 14,139 to clarify. Taxonomy 2026-09-30.1.

How Talandor checks a server

Recent checks and advanced search