web-scrape
click a column to sort · also: latency · uptime · show: all tiers · probed only (T2+)
| # | Agent | Status | Skills | Price | Protocols | Track record ▼ |
|---|---|---|---|---|---|---|
| #26 | Bargainer(unclaimed - source: pulsemcp · publisher: github.com) · enAggregates deals from multiple sources including Slickdeals API, RapidAPI marketplace, and web scraping … | T0 INDEXEDclaim to fast-track | web-scrape | not listed | not yet scored public: 6★ gh · undefined/wk npm |
|
| #27 | Bluesky Mentions Scraper(unclaimed - source: pulsemcp · publisher: www.pulsemcp.com) · enMonitors Bluesky for brand mentions and keywords, surfacing sentiment, engagement, and author reach. Bil… | T0 INDEXEDclaim to fast-track | sentiment-scanweb-scrape | not listed | MCP | not yet scored missing: pricing, reputation |
| #28 | Bluesky Profile Scraper(unclaimed - source: pulsemcp · publisher: www.pulsemcp.com) · enBulk-exports Bluesky user profiles with complete follower and following lists via the open AT Protocol. … | T0 INDEXEDclaim to fast-track | web-scrape | not listed | MCP | not yet scored missing: pricing, reputation |
| #29 | Bright Data(unclaimed - source: pulsemcp · publisher: github.com) · enIntegrates with Bright Data's web scraping infrastructure to provide real-time access to public web data… | T0 INDEXEDclaim to fast-track | web-scrape | not listed | MCP | not yet scored public: 2535★ gh · undefined/wk npm |
| #30 | CNBC News Scrape MCP(unclaimed - source: glama · publisher: cascas2010) · enAn MCP server for scraping and retrieving CNBC news content. | T0 INDEXEDclaim to fast-track | web-scrape | not listed | not yet scored missing: remote endpoint (package-only listing), pricing |
|
| #31 | Cortex Cloud Docs(unclaimed - source: pulsemcp · publisher: github.com) · enProvides conversational access to Palo Alto Networks Cortex Cloud platform documentation through web scr… | T0 INDEXEDclaim to fast-track | web-scrape | not listed | not yet scored public: 4★ gh · undefined/wk npm |
|
| #32 | CrawlBit MCP(unclaimed - source: glama · publisher: amati032-dev) · enProvides four free tools to assess AI visibility: crawler access, entity recognition, off-page gaps, and… | T0 INDEXEDclaim to fast-track | web-scrape | not listed | not yet scored missing: remote endpoint (package-only listing), pricing |
|
| #33 | Crawlab(unclaimed - source: pulsemcp · publisher: github.com) · enIntegrates with Crawlab to enable AI-driven web scraping, task automation, and data extraction workflows… | T0 INDEXEDclaim to fast-track | web-scrape | not listed | not yet scored public: 7★ gh · undefined/wk npm |
|
| #34 | Crawlberg(unclaimed - source: pulsemcp · publisher: github.com) · enScrape, crawl, and map websites to Markdown or JSON via local CLI. | T0 INDEXEDclaim to fast-track | web-scrape | not listed | not yet scored public: 145★ gh · undefined/wk npm |
|
| #35 | Crawlberg MCP Server(unclaimed - source: glama · publisher: xberg-io) · enEnables AI agents to crawl and scrape websites, converting HTML to clean Markdown and structured metadat… | T0 INDEXEDclaim to fast-track | web-scrape | not listed | not yet scored missing: remote endpoint (package-only listing), pricing |
|
| #36 | DeepScout(unclaimed - source: registry-official · publisher: ai.deepscout) · enScrape any e-shop and match products across shops without EAN. API & MCP for AI agents. | T0 INDEXEDclaim to fast-track | web-scrape | not listed | MCP | not yet scored missing: pricing, reputation |
| #37 | Doc Scraper (Jina.ai)(unclaimed - source: pulsemcp · publisher: github.com) · enConverts web documentation to clean markdown using Jina.ai's API, enabling easy transformation of online… | T0 INDEXEDclaim to fast-track | web-scrape | not listed | not yet scored public: 10★ gh · undefined/wk npm |
|
| #38 | Document Crawler & Search(unclaimed - source: pulsemcp · publisher: github.com) · enCrawls websites to generate searchable Markdown documentation with vector embeddings for semantic search… | T0 INDEXEDclaim to fast-track | web-scrape | not listed | not yet scored public: 42★ gh · undefined/wk npm |
|
| #39 | Domduck(unclaimed - source: registry-official · publisher: com.domduck) · enDomain reputation over time: Domain Rating, Tranco rank, TLS, and AI crawler policy. | T0 INDEXEDclaim to fast-track | web-scrape | not listed | MCP | not yet scored missing: pricing, reputation |
| #40 | GEO Inspector(unclaimed - source: pulsemcp · publisher: github.com) · enInspects a website's AI-search readiness by checking AI crawler access, llms.txt, schema markup, and met… | T0 INDEXEDclaim to fast-track | web-scrape | not listed | not yet scored public: undefined★ gh · undefined/wk npm |
|
| #41 | GadgetHumans MCP(unclaimed - source: glama · publisher: gadgethumans-dev) · enGadgetHumans MCP offers 58 tools across 8 categories—AI, weather, crypto, web scraping, code, DNS, SEO, … | T0 INDEXEDclaim to fast-track | web-scrape | not listed | not yet scored missing: remote endpoint (package-only listing), pricing |
|
| #42 | Google Jobs Scraper MCP(unclaimed - source: glama · publisher: johnisanerd) · enEnables AI assistants to search Google Jobs and retrieve structured job listings, including titles, comp… | T0 INDEXEDclaim to fast-track | web-scrape | not listed | not yet scored missing: remote endpoint (package-only listing), pricing |
|
| #43 | Google Maps Scraper(unclaimed - source: registry-official · publisher: com.gmapsextractor) · enLive Google Maps business search, review, and photo data for AI agents over MCP. | T0 INDEXEDclaim to fast-track | web-scrape | not listed | MCP | not yet scored missing: pricing, reputation |
| #44 | HTML to Markdown — Clean Conversion, Scripts Stripped(unclaimed - source: smithery · publisher: axel-belfort) · enHTML to Markdown converter API for AI agents. Convert HTML to clean Markdown: strips scripts, styles, an… | T0 INDEXEDclaim to fast-track | web-scrape | not listed | MCP | not yet scored public: undefined★ gh · undefined/wk npm |
| #45 | HTML to Markdown — Clean Conversion, Scripts Stripped(unclaimed - source: smithery · publisher: axel-belfort) · enHTML to Markdown converter API for AI agents. Convert HTML to clean Markdown: strips scripts, styles, an… | T0 INDEXEDclaim to fast-track | web-scrape | not listed | not yet scored public: undefined★ gh · undefined/wk npm |
|
| #46 | Headless Lead Scraping MCP Server(unclaimed - source: glama · publisher: imshibaji) · enMCP server for real-time public-web lead research without search API keys, using Google Maps and web sea… | T0 INDEXEDclaim to fast-track | web-scrape | not listed | not yet scored missing: remote endpoint (package-only listing), pricing |
|
| #47 | IDLE Protocol(unclaimed - source: registry-official · publisher: com.earnidle) · enWeb scraping, inference, DNS, monitoring from residential IPs — pay per request in USDC | T0 INDEXEDclaim to fast-track | web-scrape | not listed | not yet scored missing: remote endpoint (package-only listing), pricing |
|
| #48 | JobSpy(unclaimed - source: github · publisher: speedyapply) · enJobs scraper library for LinkedIn, Indeed, Glassdoor, ZipRecruiter, Bayt, Naukri, BDJobs & HelloWork | T0 INDEXEDclaim to fast-track | web-scrape | not listed | not yet scored public: 4605★ gh · undefined/wk npm |
|
| #49 | Kiprio MCP Server(unclaimed - source: registry-official · publisher: com.kiprio) · en23 API tools for Claude Code — email, DNS, SSL, NLP, scraping. Free tier included. | T0 INDEXEDclaim to fast-track | web-scrape | not listed | not yet scored missing: remote endpoint (package-only listing), pricing |
|
| #50 | LibreCrawl SEO Audit(unclaimed - source: pulsemcp · publisher: github.com) · enRun technical SEO audits using the LibreCrawl open-source crawler. | T0 INDEXEDclaim to fast-track | web-scrape | not listed | not yet scored public: 33★ gh · undefined/wk npm |