Remote MCP servers
43,189 servers you connect by URL over streamable HTTP. Nothing to install or keep running on your machine.
Filters · 2
Trust
Language
Category
24 results
ServerCapabilitiesStars · 30d
43,189 servers you connect by URL over streamable HTTP. Nothing to install or keep running on your machine.
A remote MCP server runs on someone else's infrastructure and your client connects to it by URL over streamable HTTP (older servers use SSE). Sign-in usually happens through OAuth in the browser instead of an API key in a config file.
Local servers run as a process on your machine and can reach your files and private network. Remote servers need no runtime and update themselves, but your data goes to the provider. Pick remote for SaaS products, local for files, databases on your network and anything offline.
In Claude Code run claude mcp add --transport http <name> <url>. In Cursor and Gemini CLI add the URL under mcpServers; in VS Code add it under servers with "type": "http". Each server page has the exact config.
Lets an AI client run browser tasks in a real Chrome browser, including fills forms, clicks, extracts data, and downloads files.
$claude mcp add browser-use -- uvx browser-use
Automates browser-based workflows using LLMs and computer vision to navigate websites, fill forms, and extract structured data.
$claude mcp add --transport http skyvern https://api.skyvern.com/mcp/
Enables AI models to scrape any URL, render JavaScript, extract structured data, and access geo-restricted web content from over 195 countries.
$claude mcp add oxylabs-mcp-d8b641 -- uvx oxylabs-mcp
Converts URLs into screenshots, PDFs, or structured JSON data for AI agents.
$claude mcp add agentrender-mcp -- uvx agentrender-mcp
Lets an AI client search the web, fetch pages as markdown, scrape structured content, and crawl websites via a unified API.
$claude mcp add clawifi-mcp -- uvx clawifi
Clones web pages into verified offline HTML copies, embeds, or rebuilds for AI coding agents using Playwright.
$claude mcp add webembedding -- npx -y web-embedding
Run and manage autonomous computer-use agents that can browse the web or control desktops through an MCP client.
$claude mcp add --transport http hai-agents-python https://agp.hcompany.ai/mcp
Captures website screenshots, manages bulk captures, and handles screenshot scheduling and history via an API.
$claude mcp add --transport http allscreenshots-plugin https://mcp.allscreenshots.com/mcp/v1
Enables AI agents to browse and interact with websites using your existing authenticated sessions through an encrypted local browser.
$https://github.com/romaklym/assertify/releases/download/v0.7.0/assertify.mcpb
Lets an AI client drive a stealth Camoufox browser in Docker with real OS-level input through a JSON HTTP API and MCP server.
$claude mcp add docker-stealthy-auto-browse -- docker run -i --rm docker.io/psyb0t/stealthy-auto-browse:v3.5.1
Lets AI agents search the web, extract page content, and look up versioned library documentation without API keys.
$claude mcp add wet -- uvx n24q02m-wet
Enables AI agents to scrape websites with JavaScript rendering, captcha solving, and structured markdown or JSON output.
$claude mcp add finedata-mcp -- uvx finedata-mcp
Scrape, crawl, and monitor public web pages as clean Markdown with change tracking and source receipts.
$claude mcp add --transport http apex-flow-web-scraper https://webscraper.apexflowlabs.com/v1/mcp
Converts websites and linked documents into clean Markdown optimized for LLMs and RAG applications.
$claude mcp add --transport http website-to-markdown https://mcp.apify.com/?tools=prometheus-maker/website-to-markdown-crawlerCaptures full-page, mobile, or element screenshots of any URL in PNG, JPEG, or PDF formats.
$claude mcp add --transport http website-screenshot https://mcp.apify.com/?tools=prometheus-maker/website-screenshot
Converts web pages into structured JSON containing product data, tables, and metadata, or clean Markdown for AI agents.
$claude mcp add --transport http webextract https://api.webextract.dev/mcp
Scrape, crawl, and monitor websites to extract clean markdown, structured data, and track content changes over time.
$claude mcp add --transport http mesharc-python https://mcp.mesharc.dev/mcp
Enables AI assistants to control Android devices and web browsers by interacting with the screen, apps, and accessibility trees.
$claude mcp add --transport http melaya-mcp https://api.melaya.org/mcp
Extract image URLs or download all images from any website with metadata like dimensions, format, and alt text.
$claude mcp add --transport http website-image-downloader-examples https://mcp.apify.com/?tools=sste/website-image-downloader
Enables AI agents to perform Cloudflare-bypassing web scraping, monitor Polymarket whale activity, and audit on-chain contract security.
$claude mcp add --transport http stealthguard-402 https://stealthguard-402.onrender.com/mcp