MCP servers and skills: search, filter by where they run, and compare.
A powerful Model Context Protocol (MCP) server that provides an all-in-one solution for public web access.
in the readmestructured data - **Page scraping** — any URL as Markdown or HTML, with bot detection, CAPTCHA solving, and proxy rotation handled automatically on every request - **Structured data (Web
Node.jsMIT★ 2.7kNo key
Browser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browser
in the readmebrowser profile, keeping you logged into all your services. - 🥷🏼 Stealth: Avoids basic bot detection and CAPTCHAs by using your real browser fingerprint. ## Contributing This repo contains
Node.jsApache-2.0★ 7.2kNo key
Talk, and a team of bots does the work in a real browser, a shell and your files while she keeps talking. Open source, runs on your machine, on your ChatGPT plan or an OpenAI key. npx thursday-agent
in the readmedead call. So anything slower than a few seconds goes to a bot, and she keeps talking — interrupt her, change the subject, or ask how the
Node.jsMIT★ 49No key
Anti-detection browser server for AI agents — REST API wrapping Camoufox engine with OpenClaw plugin support
in the readmeStandard browser automation (Puppeteer, Playwright, Selenium) is easily detected by modern anti-bot systems. JavaScript-level patches are fragile and get bypassed quickly. **The Solution**: CamoFox
Node.jsMIT★ 420No key
MCP server for stealth browser automation via Camoufox — 100+ tools, npx install, anti-bot stealth
Node.jsMIT★ 21No key
Web scraping MCP server for Claude, Cursor, Windsurf & AI agents — scrape any site, extract structured data, take screenshots. Anti-bot bypass, proxy rotation, authenticated scraping.
Node.jsMITFew starsNo key
2Captcha MCP server for AI agents with web search, web scraping, browser automation, captcha solving, and scalable web data collection.
in the readmefor AI agents, web scraping and browser automation Web scraping with anti-bot bypass, marketplace parsing to structured JSON, and CAPTCHA solving for AI agents over
Node.jsMIT★ 29No key
Official ZenRows MCP integration
in the readmebots.** Get reliable access to protected sites at scale, without building anti-bot handling yourself. - **Managed web data infrastructure.** Proxy rotation, headless browser orchestration, anti-bot
Node.jsMIT★ 20No key
Drop-in replacement for the official fetch MCP: clean, LLM-ready Markdown from any URL. JS rendering, anti-bot, honest errors, SSRF-safe. Zero-config, $0.
Node.jsMITFew starsNo key
Native Safari browser automation for AI agents. 98 tools via AppleScript — zero overhead, keeps logins, runs silently in background. Drop-in alternative to Chrome DevTools MCP with 40-60% less CPU/hea
in the readmesecond browser - **Relies on headless scrapers** — blocked by Cloudflare, reCAPTCHA, and bot detection ## ✅ With Safari MCP Your AI drives the **Safari you're already logged into
Node.jsMIT★ 217No key
ESLint for AI search — audit AI crawler access, llms.txt, structured data and citability for ChatGPT, Perplexity, Claude & co.
in the readmeover from staging, a client-rendered page that looks empty to a bot that doesn't run JavaScript. - **Existing tools are blocklists or score-only web
Node.jsMIT★ 3Few starsNo key
Anti-detection browser MCP server for AI agents — navigate, interact, and automate the web without getting blocked
Node.jsMIT★ 117No key
Unofficial OpenEvidence MCP server — query OpenEvidence from Claude Code, Codex, and any MCP client through your own logged-in browser tab (no API key). Fire-and-forget asks, a shared relay daemon for
in the readmetab. No API key. ## What it does OpenEvidence protects its API with bot detection that blocks plain server requests. This project removes that problem: when your
Node.jsApache-2.0★ 78No key
Browser automation CLI on raw CDP — no Puppeteer, Playwright or Selenium, 0 npm dependencies. 70+ commands, test assertions, click/fill by visible text without an LLM, and an MCP server for AI coding
in the readmecommands** — Navigate, click, type, screenshot, network, console, accessibility, video understanding, progressive anti-bot resilience, and more - **AI-agent friendly** — Designed for Claude, GPT, Gemini, and any
Node.jsMIT★ 32No key
The browser tool that can stop and ask you. A 2FA code, a CAPTCHA, a choice only you can make: it asks on your screen, then carries on in the same signed-in Chrome. 40 tools, MCP clients that run loca
in the readmeyour sessions, your 2FA. So it works on CAPTCHA, 2FA and anti-bot sites where Playwright and Puppeteer get blocked - because it's *you* browsing. The
Node.jsMIT★ 54No key
Framework-agnostic Spintax engine for JavaScript/TypeScript — parse, render, validate, extract. Zero-dep; runs on Cloudflare Workers, Node, and the browser. Published as @spintax/core.
in the skill textWorker > (`examples/worker`, M4). See the spec and `packages/core` . ## Try it live 🎮 - 🤖 **Telegram bot — @spintaxnetbot ** — paste a spintax template and it validates it and replies with random
SkillMIT★ 2Few starsNo key
MCP server for AI agents to read any web page in full — past the robots.txt and bot blocks that stop native fetch — as clean, ad-stripped Markdown. Plus web search.
Node.jsApache-2.0Few starsNo key
Check whether a page is scrapeable before the scraper is written, and say when it cannot tell
in the readmeand see what will block your scraper — before you write it Anti-bot vendors, rate limits, robots.txt rules, login walls, console errors, screenshots --- > **Useful?** A star
Node.jsMIT★ 1Few starsNo key
Residential proxy MCP for AI agents — bypass Cloudflare and anti-bot walls. npm: novada-proxy-mcp.
Node.jsMIT★ 4Few starsNo key
Zero-config CLI that gives AI agents reliable access to protected web data through Zenrows — Fetch, Extract, Batch, and Browser Sessions, plus MCP setup and agent skills. No API key needed to start.
in the readmeagent can reliably access protected web data without hand-rolling anti-bot handling, proxies, or browser rendering. --- ## 1. What this is A single, dependency-light CLI
Node.jsMIT★ 16No key
Model Context Protocol (MCP) server for ScrapeUnblocker - let Claude fetch any web page's HTML through your own API key.
in the readmeplugins** that return structured JSON - through the ScrapeUnblocker scraping API, bypassing anti-bot protection (Cloudflare, DataDome, PerimeterX, Akamai, Shape). You bring your **own** API key. Nothing
Node.jsMIT★ 1Few starsNeeds a key
Local-first MCP server and CLI in Rust: any page as LLM-ready Markdown, whole-site crawls, keyless search, and local captcha solving. No cloud, no API keys.
Node.jsAGPL-3.0★ 19No key
CapMonster Cloud MCP server for Patchright — AI captcha solver for stealth browser automation. Let AI agents bypass reCAPTCHA, Turnstile & DataDome through a Patchright-driven browser via MCP.
in the readmesends | ❌ removed | | `--enable-automation` flag | ✅ present | ❌ removed | | `navigator.webdriver` | `true` | `false` / `undefined` | | Anti-bot evasion | ❌ | ✅ | See the full comparison for details. ## Quick start ```bash npm
Node.jsMIT★ 1Few starsNo key
A powerful Model Context Protocol (MCP) server that provides an access to serverless browser for AI agents and apps
in the readmerobust infrastructure to manage complexities such as bypassing geo-restrictions and bot detection mechanisms. 4. The server then delivers the structured data or action outcome back
Node.jsMIT★ 35No key
A MCP (Model Context Protocol) server that provides get, send Gmails without local credential or token setup.
Node.jsMIT★ 55No key
Official CapMonster Cloud MCP server — AI captcha solver for reCAPTCHA v2/v3, Cloudflare Turnstile & DataDome. Let Claude, Cursor, and other AI agents solve captchas directly via MCP.
in the readmemanaged challenge / `cf_clearance`) - **FunCaptcha** (Arkose) - **GeeTest** (v3 and v4) - **Enterprise Anti-Bot Systems:** AWS WAF, DataDome, Imperva, TSPD, Binance, Prosopo, Yidun, TenDI, Hunt, Altcha, Basilisk
Node.jsMIT★ 3Few starsNo key
Single-file, zero-dependency MCP server giving Claude, Cursor and any MCP client live web access.
in the readmesolved (`blockClass: "captcha"`). | | `seo_audit` | Fetch a URL as a no-JS bot **and** fully rendered, return both SEO views + the diff (JS-only content, changed
Node.jsMITFew starsNo key
Web search and web fetch for AI agents. One small binary, no API keys, and it reads the sites that refuse your agent.
in the readmesource, from the makers of AliasMode . Agent harnesses fetch pages with a bot identity, and a large part of the web answers `403`. Anyfetch sends the
Node.jsApache-2.0Few starsNo key
MCP server for AI visibility: audit crawler permissions, llms.txt, and structured data from any AI agent
in the readmewith fixes | | `check_ai_crawlers` | "Is GPTBot blocked?" — robots.txt policy per AI bot | `{ url }` | Per-bot allow/block verdicts with the matching rule, plus sitemaps | | `inspect_llms
Node.jsMITFew starsNo key
Tiny CLI and MCP server: fetch an URL -- return clean markdown. Built for AI agents.
in the readmethan you'd like. `markfetch` sends **a coherent Chrome header set** so bot-detection systems see a real browser, then runs the response through the **same
Node.jsMIT★ 3Few starsNo key
Renders JavaScript-heavy pages in a real browser so agents can read them.
in the readmemakes, with JSON bodies). - Says when a page isn't the page: bot checks, login walls, HTTP errors, and empty renders come back labelled, with what
Node.jsMITFew starsNo key
Crawlbase MCP Server connects AI agents and LLMs with real-time web data. It powers Claude, Cursor, and Windsurf integrations with battle-tested web scraping, JavaScript rendering, and anti-bot protec
MCPLink only★ 58
Keyless web search and page reading for AI agents. CLI, MCP server and HTTP API that gets past bot walls.
Node.jsApache-2.0Few starsNo key
Stealth Chromium MCP server with hybrid AOM + Set-of-Mark vision. Patchright-grade anti-detection. Token-lean by default.
in the readmeRuntime.Enable` CDP leak that bypasses `playwright-extra`-class stealth plugins. Passes modern bot-detection suites (CreepJS, bot.sannysoft.com) where vanilla Playwright fails. - **Token-lean by default.** `browser
Node.jsApache-2.0★ 1Few starsNo key
⚡ Official MCP Server & OpenAPI 3.1 Gateway for M2M Market — Freedom Engine (100/100 Verified SLA). Pay per call via Bitcoin Lightning (L402) or Base/Solana USDC (x402). Stealth Web Unlocker, Structur
in the readmehealing fetcher rotating realistic desktop browser headers (Chrome/Safari/Firefox) to bypass standard anti-bot filters, returning clean Markdown, OpenGraph metadata, and `JSON-LD`. | | `freedom_structured_extractor
Node.jsMITFew starsNo key
Tock (exploretock.com) MCP: discover restaurants, search a metro, get venue details and availability. Relays through your signed-in browser tab via the fetchproxy bridge.
in the readmebrowser tab via the ContextMint Bridge browser extension — no cookie paste, no bot-wall dance, no password handling. This project was developed and is maintained
Node.jsMITFew starsNo key
Claude Code 的全交互对外抓手 MCP —— 搜/抓/登录态抓/控桌面(macOS·Win·Linux)，四通道+多引擎 fallback+cookie AES-256+markdown 抽取，一个 MCP 全包。 | All-in-one interaction MCP for Claude Code — search / scrape / logged-in browse / con
in the readme做完了会确认） | | 「直接取这个 JSON 接口的返回值」 | 原始字节（最快最省） | | 「这个站好像有点反爬，试试看」 | `browse_headless` 自带反检测（过基础 bot 检测），很多站点直接能抓，无需配置 | | 「这个站有 Cloudflare 我抓不动」 | 云端 Chrome 反爬——**Steel 自托管（免费）** 或
Node.jsMITFew starsNo key
MCP server that drives chat.sakana.ai via headless Chrome — persistent sessions for AI assistant use
in the readmefor Improvements** > `chat.sakana.ai` has updated its internal endpoints and introduced Cloudflare Turnstile bot protection, causing `chat_send` to fail with headless Chrome. This MCP is currently
Node.jsMITFew starsNo key
Archive any URL to a shareable snapshot (rrweb/pdf/png) + agent-driven web QA — an MCP server for siteglass.io. No CAPTCHA, no signup.
in the readmepage **PNG**. No CAPTCHA, no signup, no ownership check, callable programmatically — a bot-friendly alternative to archive.today. (It renders JS-heavy pages; it does *not* produce
Node.jsMITFew starsNo key
A MCP server for DuckDuckGo HTML search.
in the readmeReturns title, URL, and snippet for each result - Caches results - Retries on bot detection ## Usage ```bash bunx --silent duckduckgo-mcp@latest ``` OpenCode ```json { "$schema": " "mcp": { "duckduckgo
Node.jsISCFew starsNo key
A MCP server that provides a web crawling and content extraction tool for AI assistants
in the readmeany public web page. - Uses Puppeteer with stealth plugin to bypass anti-bot protections. - Returns readable, whitespace-normalized text for LLM consumption. - Easy integration with Claude
Node.jsMIT★ 1Few starsNo key
MCP server backed by CloakBrowser stealth Chromium. Drop-in @playwright/mcp replacement with source-level fingerprint patches and 80 tools. Bypasses Cloudflare Turnstile, reCAPTCHA v3, FingerprintJS,
MCPLink only★ 2Few stars
Residential proxy MCP server for AI agents — bypass Cloudflare/Akamai, geo-target 195+ countries, sticky sessions. Multi-provider: Novada, BrightData, Smartproxy, Oxylabs.
MCPLink only★ 1Few stars
TestChimp CLI and MCP server. Lets coding agents run QA using coverage signals, in-repo test plans and release governance.
in the readmeare set, both are sent and the backend prefers the bearer. | | `TESTCHIMP_BOT_ID` | QA bot id (sent as `bot-id` header for attribution). Must
Node.jsMITFew starsNeeds a key
Model Context Protocol (MCP) Server for Graphlit Platform
in the readmeENVIRONMENT_ID": "your-environment-id", "GRAPHLIT_JWT_SECRET": "your-jwt-secret", "SLACK_BOT_TOKEN": "your-slack-bot-token", "DISCORD_BOT_TOKEN": "your-discord-bot-token", "TWITTER
Node.jsMIT★ 378No key
Privacy-first job Agent Skill for Claude/Cursor/Codex: verified facts only, OS secrets, confirmed submissions.
in the skill textUse your preferred agent Setup templates are available for **Hermes Agent**, **Grok Bot**, and **OpenClaw**: ```bash npx job-application-agent@latest platforms npx job-application-agent
SkillMIT★ 156No key
Gives agents a real browser. URL in, pruned snapshot out. Replaces Playwright, Selenium, Puppeteer. Zero deps, zero wasted tokens.
in the readmeFast automation, scraping, reading pages | | **Headed** | Auto-launches a visible browser window | Bot-detected sites, visual debugging, CAPTCHAs | | **Hybrid** | Tries headless first, auto-launches headed
Node.jsApache-2.0★ 46No key
Record a browser workflow once, get a deterministic MCP tool your AI agent can call. Zero tokens at runtime. Postman for AI agents.
in the readmeworkflow complexity | | **Reliability** | Deterministic — same input, same output | Variable — exploration can diverge | | **Bot detection** | Real Chromium + stealth-fetch | Detectable automation fingerprint | | **Fallback** | Automatic ladder (API → DOM
Node.jsMIT★ 24No key
Who stands behind it
Who stands behind it
