← All headings
Web scraping & browsers
2,172 listings from 1,017 providers, 1,716 answering · counted
Filed by addrbook from the words in each listing, so a heading says what a listing claims to be for.
Showing 676–700, one row per provider, those answering first · names and descriptions as their source publishes them
- Diffbotio.github.diffbot/diffbot-mcp · mcp.diffbot.comWeb search, page extraction, crawling, and Knowledge Graph queries from Diffbot's web index.Live, sign-in requiredchecked Evidence 1/3MCPWebsiteMCP Registry
- LV24 SEOio.github.LevapVeeskela/lv24-seo · seo.lv24.byFree-first SEO for agents: GSC, Yandex Webmaster/Metrika, Bing, CrUX, PSI, crawl.Livechecked Evidence 1/3WebsiteMCP Registry
- YouTube Scraperio.github.coregentdevspace/youtube-scraper · mcp.rapidapi.comYouTube videos, Shorts, comments, channels, contacts and transcripts as structured JSON.Livechecked Evidence 1/3MCPWebsiteMCP Registry1 more from rapidapi.com
- Browser Coreio.github.ShuhLab/browser-core · m2g.proMCP browser automation: local Chrome, personal VPS and limited Hosted Cloud with manual handoff.Live, sign-in requiredchecked Evidence 1/3MCPMCP Registry
- MarkUDownio.github.Scrape-Technology/markudown-mcp · scrapetechnology.comWeb scraping for AI agents: scrape, crawl, search and extract any site as clean Markdown or JSON.Livechecked Evidence 1/3WebsiteMCP Registry
- extension.dev Browser Extensionsio.github.extensiondev/mcp · extension.devBuild, run, debug, test and ship Chrome, Firefox, Edge and Safari extensions from your AI agent.Live, sign-in requiredchecked Evidence 1/3MCPWebsiteMCP Registry
- SoftGlaze Browserio.github.softglazee/softglaze-browser-mcp · browser.softglaze.comAI apps run SoftGlaze Browser profiles, each with its own cookies and proxy. You approve changes.Livechecked Evidence 1/3WebsiteMCP Registry
- Scrappycocoio.github.Albert-Tam/scrappycoco · api.scrappycoco.aiRoute web, social, and filings data tasks to the best available scraper.Live, sign-in requiredchecked Evidence 1/3MCPWebsiteMCP Registry
- scrape-toll-production.up.railway.appscrape-toll-production-up-railway-appLivechecked Evidence 1/4x402Agentic.Market1 more from scrape-toll-production.up.railway.app
- Sitekick CMSio.github.aketchel/sitekick-cms · mcp.sitekick.aiPlan and improve WordPress websites with generation, previews, and browser-approved publishing.Livechecked Evidence 1/3MCPWebsiteMCP Registry
- Irmu — Web Data MCPio.github.polgoide/irmu · app.irmu.comWeb scraping, browser automation, screenshots and AI data extraction for AI agents via MCP.Live, sign-in requiredchecked Evidence 1/3MCPWebsiteMCP Registry
- API Plan Finderio.github.scraping-api-plans/web-data-plan-finder · plans.intoperson.comBest API plans + report on 46 conditions for scraping, SERP, search, browser, email, TTS, STT, docsLivechecked Evidence 1/3MCPWebsiteMCP Registry
- Arachne MCPio.github.Samuelfmedeiros/arachne · arachne.seu.petWeb scraping, browser RAG, vision, transcription, and 20 AI tools. Universal data intelligence.Live, sign-in requiredchecked Evidence 1/3MCPMCP Registry
- crawlproofcom.profullstack/crawlproof · crawlproof.comAI-crawler audits + ads (crawlproof.com)Live, sign-in requiredchecked Evidence 1/3MCPWebsiteMCP Registry
- x402 Forgeforge.fizzl.euCan I fetch this URL under the site's robots.txt? Robots.txt check: Tells a crawler or AI agent whether a robots.txt lets it crawl a given URL, and which line decides it. $0.001 per call in USDC, charged only on a 2xx answer. Try it free: https://forge.fizzl.eu/try/robots-check. Signed receipt. Own this tool for $1.00 and earn from every call: https://forge.fizzl.eu/forge/packages/robots-check.Livechecked Evidence 1/4x402x402 Bazaar
- Radio Browser MCP by UnClickio.github.malamutemayhem/radiobrowser · unclick.worldSearch internet radio stations by country, tag, popularity, and votes. No API key. By UnClick.Livechecked Evidence 0/3WebsiteMCP Registry
- GenPark Bloom Filter URL Dedup Crawlerio.github.alphaparkinc/genpark-bloom-filter-url-dedup-crawler-skill · genpark.aiIn-memory Bloom filter for URL and document hash deduplication preventing redundant web crawler ingeLivechecked Evidence 0/3WebsiteMCP Registry
- io.github.houtini-ai/seo-audit-consolehoutini.comTechnical SEO in Claude: GSC + crawl + DataForSEO - audit, portfolio, market sizing, content recon.Livechecked Evidence 0/3WebsiteMCP Registry
- io.github.CapMonsterCloud/capmonster-mcp-patchright-captcha-solvercapmonster.cloudBrowser automation MCP for solving captchas with CapMonster Cloud via Patchright.Livechecked Evidence 0/3WebsiteMCP Registry
- Eclipse Crawlwayio.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/eclipse-crawlway-mcp · eclipsebazaar.comPay-per-crawl licensing receipts: sealed identity+terms+fingerprint binding. LOCAL/fixture only.Livechecked Evidence 0/3WebsiteMCP Registry
- Printwren: HTML to PDF and URL to PDF (real Chrome)io.github.shawmena-dotcom/html-to-pdf · printwren.cybermax-tools.workers.devPrintwren: web page or HTML to PDF with real Chrome; pages, base64 or download link. Free, no key.Livechecked ContradictedMCPWebsiteMCP Registry3 more from cybermax-tools.workers.dev
- Bob Research Toolsbob.assimilatethis.comCondense one web page into a short summary. Give a URL; Bob reads the page with Firecrawl and returns an 80-word summary with key points, not the page text (use /extract for the text itself). Typical response 3 to 6 seconds. If the page cannot be read in time you get an error and are not charged.Livechecked Contradictedx402x402 Bazaar9 payers1 more from assimilatethis.com
- Macaroon Networkapi.macaroonnetwork.comReal-time GPU and LLM API pricing data scraped from public cloud provider websites. Structured, parsed pricing with per-provider plan details, source URLs, content hashes, and freshness. No outbound network on purchase — data is read from the local feed database populated by the scraper on a 6-hour cadence.Livechecked Contradictedx402x402 Bazaar5 payers
- x402 Web Toolsweb.kagurazaka.devFetch a public web page and return its main content as clean Markdown (Mozilla Readability, as in Firefox Reader View, then Markdown with absolute links and tables), with title, byline, site name, published date, language, excerpt and a token estimate. Navigation, ads and footers are left out. Pages that cannot be read (errors, not HTML) are not charged.Livechecked Contradictedx402x402 Bazaar3 payers2 more from kagurazaka.dev
- Rooms by Aurmadarooms.aurmada.comUse it when you need the readable text of a public web page as clean markdown without running a browser: articles, docs, blog posts, product pages. Returns title, byline, excerpt, word count, language and up to 100 absolute links (Mozilla Readability, no AI model). 2 MB and 8 s limits; private and internal addresses are refused. Never charged for errors: we settle the payment only after a successful answer.Livechecked Contradictedx402x402 Bazaar3 payers