Remote MCP servers let a supported client connect to a hosted endpoint. You do not need to launch that server as a local process, but you still need a compatible client, network access and the authentication required by the service.
A service's homepage or GitHub repository is not interchangeable with its MCP URL. Copy the documented endpoint and choose the transport the service supports. Older SSE configurations and Streamable HTTP configurations can differ; adding an arbitrary path to a website will not turn it into an MCP server.
OAuth connections authorize an account through the provider's sign-in flow. API-key connections require the documented header or credential setting. Confirm the workspace and scopes before asking an assistant to read private data or write to a service. A successful connection does not prove it has permission to every resource.
Check that the endpoint is reachable, the client supports its transport and authentication, and the credentials belong to the intended account. Then inspect the tool list and try one simple read. If connection works but a tool fails, review resource permissions and the tool's required arguments.
Start with Figma's official server, Notion or GitHub when those services match your task. Browse official integrations and the full directory for other options.
28,952 servers · Page 363 of 483
The Google for AI agents — company intel, competitor tracking, market research via MCP. JSON output
B2B data for AI agents: lead lookup, deliverability scoring, domain intel. x402 $0.01-$0.03/call.
Find business leads and live opportunities for a business, with the proof and the next step.
Instant Canadian scrap-car value quotes by year/make/model, provincial rates, and pickup leads.
Pay-per-call agent tools via x402 (USDC on Base): chat, prices, funding, RNG. No account or keys.
Unified social scraper MCP — profiles, posts, videos across ~40 platforms via Streamable HTTP.
Here for the offline verifier? It's in this repo: tools/verify-verdict.mjs — one file, no dependencies, verifies any ScrapeCheck verdict with no network access. How to use it →
ScrapeCreators MCP — wraps the ScrapeCreators social-media + ad-library
Google Maps, LinkedIn, Instagram, TikTok and X data as tools. Demo mode needs no key.
Enable language models to perform advanced AI-powered web scraping with enterprise-grade reliabili…
A production-ready [Model Context Protocol](https://modelcontextprotocol.io/introduction) (MCP) server that provides seamless integration with the
Integrate real-time Scrapeless Google SERP(Google Search, Google Flight, Google Map, Google Jobs....) results into your LLM applications. This server
Pay-per-call YouTube data via x402 (USDC, Base): search, channels, playlists, video details, comment
Pay-per-call x402 Amazon product, search and review data for AI agents. USDC on Base, no API key.
Pay-per-call x402 arXiv paper search, metadata, abstracts, and category listings.
Pay-per-call x402 SEC EDGAR data: company search, profiles, XBRL financials, filings.
Pay-per-call x402 DNS, WHOIS/RDAP, availability, email security, SSL check, CT subdomains.
Pay-per-call x402 Base/Ethereum: prices, DEX prices, ENS/Basenames, gas, tokens, balances, txs.
Pay-per-call x402 npm and PyPI package metadata, versions, search, download counts.
Pay-per-call x402 ECB FX rates/conversion, time zones, weather forecasts, Hacker News.
Pay-per-call x402 stock, ETF, index, FX and crypto quotes, OHLCV history, ticker and coin search.
Pay-per-call x402 web reading: page to Markdown, link previews, RSS feeds, links, sitemaps.
Pay-per-call x402 web search results, news search and search autocomplete suggestions for agents.
Pay-per-call x402 Bluesky search, profiles, feeds; Hacker News search and threads; Lobsters.
Pay-per-call x402 Wikipedia summaries/search and Wikidata facts, with CC BY-SA attribution.
Web search, scraping, RAG answers with citations, and translation as MCP tools.
ScraperAPI MCP — wraps ScraperAPI (scraperapi.com), a proxy-based web
One API for public web data across social, directories and real estate, as clean JSON.
Current pricing, cost estimates and recommendations for web scraping APIs, with official sources.
ScrapeUnblocker: ScrapeUnblocker allows to bypass anti-bot services and scrape the full page source.
Fetch any page's HTML or AI-parsed JSON, Google results, or 100+ site plugins via ScrapeUnblocker
Web data for marketing agents: traffic, ads, social profiles, search, and any URL as markdown.
Scrape, clean and match product and price data from any website
Give it a URL, get structured rows. A model writes the parser once; replays are free.
The Scrapfly MCP Server connects your AI assistants to live web data through the Model Context Protocol. Transform your AI from being limited by training data to having real-time access to any…
An MCP (Model Context Protocol) server that lets AI agents fetch and read web pages. Simply give it a URL, and it returns clean, LLM-ready content — fast.
MCP server for using ScrAPI to scrape web pages.
ScrapingAnt MCP — wraps the ScrapingAnt web scraping API (scrapingant.com)
ScrapingBee MCP — wraps the ScrapingBee headless-scraping API (scrapingbee.com)
Scrape any web page, search Google/Amazon/Walmart/YouTube and extract data via the ScrapingBee API.
Public web data for AI agents: scrape any page, plus Google, TikTok, Instagram and Amazon as JSON.
Scrapingdog MCP — wraps Scrapingdog (scrapingdog.com), a proxy-based web
Any URL to clean text, markdown, or JSON for LLM/RAG pipelines.
Scraping API for Google Search, Maps, Flights, Jobs, YouTube, LinkedIn, Trustpilot and more.
Route web, social, and filings data tasks to the best available scraper.
Household-aware cooking brain: pantry, meal suggestions, dietary safety, recipes, shopping lists.
Detailed breakdown of a person's or company's credit operations in Brazil's Central Bank SCR, by ref
Summary of a person's or company's credit operations in Brazil's Central Bank credit information sys
SCREAMING_SNAKE charset, value discarded
scream-void MCP — wraps StupidAPIs (keyless — no credential needed)
Narrated demo and tutorial videos of your web app, from a guide or your coding agent.
Generate designed, localized App Store screenshot sets from your raw app captures.
OFAC and global sanctions screening: crypto addresses, emails, websites, IDs, countries, VPN, geo
Design and export App Store / Play Store screenshots, localized across all 48 App Store locales.
screenpipe remembers how you actually work It captures what you see, say, and do, locally, 24/7, then turns real work into searchable memory, SOPs
Real product UI captures (onboarding, pricing, in-app screens) with design guides for coding agents.
Research mobile apps, onboarding, paywalls, and competitors with real screens, flows, and reviews.
Sanctions screening for AI agents: check a name against OFAC and EU lists. Free during launch.
Pixel-perfect webpage screenshots rendered in a real browser, full-page or viewport, via one POST.
Screenshot any URL/HTML as PNG/JPEG/WebP, or read it as clean Markdown/text for LLMs.