"Cloud Foundry" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Search YouTube and read video, channel and transcript data as JSON. No Google Cloud project.
Google SERP as JSON: organic, AI Overview, People Also Ask, AI Mode, news, shopping. No Cloud setup.
Google Maps places, reviews, contributor history, photos and posts as JSON. No Google Cloud.
Undetectable cloud browser sessions for AI agents and scrapers. Navigate, extract, click, captcha.
Browser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data.
Verified websites as JSON commands for AI agents over plain curl or MCP.
Zyte MCP is a remote MCP server that lets an agent use Zyte on your behalf. It can download pages with a plain HTTP request or in a real browser, click and type and take screenshots, and pull structured data out of a page with AI, either as a standard type like product, article or job posting or as fields you describe in plain words. It can also search the web from a chosen country, check whether Zyte API supports a site and what a request costs, and report your usage by domain. If you have Scrapy Cloud projects, the same server can list spiders, start and cancel jobs, read logs and items, manage schedules and settings, and read and write collections. Those tools can change and delete things, so review what your agent asks to do. Connect to https://mcp.zyte.com/v1/mcp and sign in to your Zyte account with OAuth. Using the server is free. What your agent does through it is billed at Zyte API prices, on a dedicated mcp_access_key you can track and cap. New accounts get $5 of trial credit for a month.
Managed cloud browser, browser automation, and web data extraction API for developers and AI agents. Remote HTTP MCP endpoint. Requires an AdsCrawl API key in the x-api-key header. Website: https://www.adscrawl.net
- BrowserlessOAuth via extensionio.browserless.mcp
Browserless MCP - Cloud browser automation for AI agents with bot-detection bypass. Scrape and crawl sites, take screenshots, generate PDFs, run headless Chrome functions or an autonomous browsing agent, all through MCP.
Hosted remote MCP server for AI-driven stealth browser automation. Connect any MCP client (Cursor/Cline natively, Claude Desktop via mcp-remote) — no install, no Docker, no Playwright. Drives a real Chromium with residential proxies, automatic CAPTCHA solving, persistent profiles, and a live viewer URL for human-in-the-loop. Three tools: humanbrowser_run, humanbrowser_stream, humanbrowser_viewer_url. Same hb_live_* Bearer token works for both MCP and the A2A 1.0 endpoint.
Fetch pages as markdown or HTML, search the web and news, and extract JSON-LD structured data. Built for AI agents. $2.50/1k requests, 500 free on signup.
Read, crawl and act on websites, signed in as the user, and turn any site into an API.
Pay-per-call APIs for AI agents: web scraping, DNS/email checks, classification, trading risk.
Fetch pages as markdown, search web and news, extract structured data. For AI agents.
- eco-mcp-fetchOAuth unavailableio.github.FindDataTechnology
[生态] modelcontextprotocol 官方参考实现（MIT） — 想 7×24 常驻 → 萬星
Cloud browsers for AI agents: saved logins, residential IPs, live human takeover, 57 browser tools.
Capture website screenshots (viewport or full page) with local Chrome, or on OpenScreenShot Cloud.
Cloud-based web access with real browsers and JS rendering by ScrapingAnt
Oracle Recruiting Cloud (HCM) career-site jobs as JSON for any company: full JD, dates. $2/1k
Cloud file relay: chunked uploads, folders, share links, inline text reads, ZIP packing.
