Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
Looks like a goal we have a starting path for: I want to research potential clients
-
tweetclaw
SkillsOpenClaw Twitter plugin, a Twitter bot for automation, to scrape tweets & export followers. Not affiliated with X Corp.
git clone https://github.com/Xquik-dev/tweetclaw.git -
Dataflow Kit Web Scraper
Public APIsRender Javascript driven pages, while we internally manage Headless Chrome and proxies for you. - Build a custom web scraper with our Visual point-and-click toolkit. - Scrape the most popular Search engines result pages (SERP). - Convert web pages to PDF and capture screenshots. Authentication Dataflow Kit API require you to sign up for an API key in order to use the API. The API key can be…
-
Cineloop-resp
SkillsAgentic video editing engine/skill/plugin
git clone https://github.com/PaxOrcnode/Cineloop-resp.git -
Cineloop-resp
SkillsAgentic video editing engine/skill/plugin
git clone https://github.com/NinjaIntoczar2281/Cineloop-resp.git -
Cineloop-resp
SkillsAgentic video editing engine/skill/plugin
git clone https://github.com/OgreTitansmith/Cineloop-resp.git -
Oxylabs
MCP serversOxylabs MCP — Oxylabs Web Scraper API (oxylabs.io)
@pipeworx/mcp-oxylabs@0.2.1 -
olostep-mcp-server
MCP serversMCP server for Olostep — the web scraping, crawling, and search infrastructure used by top AI companies. Gives any MCP-compatible AI agent the ability to scrape, crawl, batch-extract, and search the web in real time.
git clone https://github.com/olostep/olostep-mcp-server.git -
TheCrawler
MCP serversUniversal web scraper with LLM-ready markdown, RAG chunking, PDF/DOCX support.
thecrawler@0.5.8 -
certainlyscraped
MCP serversHybrid scraper with escalating effort: cheapest fetch first, reports why each page stopped.
certainlyscraped@0.4.5 -
ShadowCrawl
MCP serversRust MCP stealth scraper: anti-bot search/scrape with CDP fallback + HITL non-robot.
-
Pulldata
MCP serversDiscover and run Pulldata scrapers, track jobs, and retrieve results from your AI client.
-
browser-forest
MCP serversUndetectable cloud browser sessions for AI agents and scrapers. Navigate, extract, click, captcha.
-
instagram
MCP serversInstagram: Instagram public data scraper API for search, users, posts, hashtags, locations and more.
-
tiktok
MCP serversUnofficial TikTok API & scraper: creator analytics, video data, comments, search. x402, no API key.
-
Scrappycoco
MCP serversRoute web, social, and filings data tasks to the best available scraper.
-
ScrapeAtlas
MCP serversUnified social scraper MCP — profiles, posts, videos across ~40 platforms via Streamable HTTP.
-
oxylabs-oxylabs-mcp
MCP serversFetch and process content from specified URLs using the Oxylabs Web Scraper API.
-
Google Maps Email Cleaner & Lead Verifier
MCP serversClean, dedupe and verify Google Maps leads from any scraper.
-
oxylabs-mcp
MCP serversFetch and process content from specified URLs & sources using the Oxylabs Web Scraper API.
oxylabs-mcp@0.10.2 -
Record Batch Gate (Dirtsmith)
MCP serversQuarantine invalid or duplicate scraper records before an AI agent writes them downstream.
dirtsmith-record-batch-gate@0.1.0 -
yandex-search
MCP serversYandex search results, images, and SERP data via the Apify Yandex Search Scraper, hosted MCP.
-
Licium
MCP serversClean rows from public pages that break ordinary scrapers, plus a bounty board where agents earn.
-
WebReaper
MCP serversAI-native web scraper: scrape, crawl and map any site to clean markdown over stdio. MIT-licensed.
WebReaper.Mcp@11.3.2 -
ReefAPI
MCP serversOne MCP server for 180+ live web-data APIs returning clean JSON from sites that block scrapers.
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.