MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package descriptions, licences and links are read from each package's own registry (npm, PyPI, crates.io, NuGet, RubyGems; Go and Maven packages are only checked to exist), and packages the registry no longer has are removed. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
@scrapeops/mcpgithub.com/scrapeops/scrapeops-mcp-serverupdated this year
MCP server for ScrapeOps Proxy API integration. Features web browsing, anti-bot bypass, JavaScript rendering, screenshots, and LLM-powered structured data extraction for AI agents.
npm MIT -
camofox-browser-pinokiogithub.com/DSRPT/camofox-browser-pinokioupdated this year
1-click Pinokio launcher for camofox-browser - a stealth headless browser for AI agents that bypasses Cloudflare, bot detection and anti-scraping. REST API with accessibility snapshots and element refs, plus an MCP server. Windows, macOS and Linux.
MIT ★ 2 -
anti-botgithub.com/TaroYamada08/anti-botupdated this year
Its fetchers bypass anti-bot systems like Cloudflare Turnstile out of the box. And its spider framework lets you scale up to concurrent, multi-session crawls. 🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!
BSD-3-Clause ★ 1 -
Web research for AI agents. Fetch any page with anti-bot bypass plus web search. $0 forever. No scrapling dependency: hound uses primp + patchright directly. Graceful degradation when browser deps are unavailable (HTTP-only mode on Termux/Android). Token-optimized tool definitions, polished cross-platform CLI, brick-proof self-update with hound doctor + rollback.
pypi MIT License -
让 AI 代理访问互联网:抓取 · 爬取 · 搜索,内置反爬,$0 无密钥。Web research for AI agents: fetch, crawl & keyless search with anti-bot bypass.
pypi NOASSERTION ★ 8 -
novada-proxygithub.com/NovadaLabs/novada-proxyupdated this year
Residential proxy MCP for AI agents — bypass Cloudflare and anti-bot walls. npm: novada-proxy-mcp.
MIT ★ 4 -
Reliable web fetching for AI agents — MCP server with retry, circuit breaker, caching, and anti-bot bypass
-
Remote MCP server for web scraping with anti-bot evasion. Gives Claude stealth HTTP fetching, headless browser, Cloudflare bypass, CSS extraction, and YouTube transcripts via Scrapling.
MIT ★ 1 -
Route AI web browsing through your home residential IP via Tailscale. Bypasses Cloudflare Turnstile, Amazon anti-bot blocks, and datacenter bans for Muse, Groq, Claude, and Cursor.
★ 25 -
playwright-mcp-humanizedgithub.com/njoppi2/playwright-mcp-humanizedupdated this year
Drop-in Playwright Tools for MCP with anti-bot curved mouse movements and log-normal typing delays. Bypasses detection by Cloudflare, DataDome, PerimeterX, etc.
npm Apache-2.0 -
AgentCrawl: Autonomous Multi-Agent Web Crawler & Anti-Bot SPA Extractor — A distributed, local-first multi-agent web crawling and structured data extraction platform engineered to bypass modern anti-bot WAFs (Cloudflare, Akamai, DataDome), hydrate dynamic SPAs, and enforce self-healing Pydantic v2 schemas.
-
Stealth web scraping API for AI agents — native MCP integration, x402 micropayments, anti-bot bypass. Returns clean Markdown from any URL.
MIT ★ 1 -
Model Context Protocol server for undetected browser automation. Drop-in replacement for server-puppeteer with advanced anti-detection capabilities to bypass bot protection systems. Built for AI agents requiring reliable web automation.
MIT ★ 1 -
Model Context Protocol server for Spider Cloud web scraping and crawling API - LinkedIn profiles, anti-bot bypass, and more
npm MIT -
A Playwright-based Python tool that bypasses Google's anti-bot mechanisms to execute searches, serving as both a command-line tool and MCP server to provide real-time search capabilities for AI assistants.
MIT ★ 6 -
Medium-Agentgithub.com/nikhilpravinpise/Medium-Agentupdated this year
📚 Turn Medium articles into audio, summaries, and AI reports. Features robust scraping with anti-bot bypass, Claude Desktop (MCP) integration, and a Gradio UI.
MIT ★ 2 -
A MCP server providing realistic browser-like HTTP request capabilities with accurate TLS/JA3/JA4 fingerprints for bypassing anti-bot measures. It also supports converting PDF and HTML documents to Markdown for easier processing by LLMs.
pypi MIT ★ 47 -
Adaptive Python web scraping toolkit + MCP server for AI agents. Self-healing selectors that survive site changes, TLS-fingerprint stealth to bypass anti-bot filters, CSS/XPath parsing, and 24 built-in scrapers, clean, structured, LLM-ready data from any URL.
pypi MIT ★ 265 -
Browserless TLS/HTTP2 bypass & handshake analyzer (BoringSSL, Rust wreq, Go uTLS) with X.509 inspection & persistent sessions for MCP, CLI & API.
MIT ★ 1 -
CapMonster Cloud stealth browser MCP server for AI agents — 66 Patchright tools for web scraping and browser automation. Pair with CapMonster Cloud MCP for captcha solving: a capsolver and 2captcha alternative.
MIT ★ 1 -
proxy4agentgithub.com/Goldentrii/proxy4agentupdated this year
Residential proxy MCP server for AI agents — bypass Cloudflare/Akamai, geo-target 195+ countries, sticky sessions. Multi-provider: Novada, BrightData, Smartproxy, Oxylabs.
npm ★ 1 -
Stealth browser automation for AI agents over MCP and the Chrome DevTools Protocol: navigation, network hooks, DOM extraction, and pixel-accurate UI cloning.
pypi MIT ★ 3,368 -
Scrape any website with Claude Code or Codex: Scrape.do MCP server, anti-bot playbook (Cloudflare, DataDome, Akamai) and self-healing scrapers that fix themselves when the site changes.
MIT -
Model Context Protocol (MCP) server for ScrapeUnblocker - let Claude fetch any web page's HTML through your own API key.
npm MIT ★ 3 -
playwright-web-fetchergithub.com/ZaZ712/playwright-web-fetcherupdated this year
Deploy a real browser to the cloud. AI-agent ready web fetching API — bypass Cloudflare, get clean content, persist sessions. curl-friendly, self-hosted, Docker-ready.
★ 2 -
webustlergithub.com/DrRuin/webustlerupdated this year
MCP server for web scraping that actually works. Extracts clean, LLM-ready markdown from any URL — even Cloudflare-protected sites.
MIT ★ 3 -
🌐 Extract clean, LLM-ready markdown from any URL, including Cloudflare-protected sites, with this effective MCP server for web scraping.
MIT ★ 1 -
Stealth Chrome MCP server - 100++ tools for AI agents. One-liner Cloudflare Turnstile bypass (proven), dual-mode HTTP with TLS fingerprint, AI Vision reCAPTCHA solver. Python + nodriver + curl_cffi + FastMCP.
pypi MIT ★ 29 -
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.
npm AGPL-3.0 ★ 21 -
HatFetchgithub.com/ProxyHatCom/HatFetchupdated this year
Give any LLM agent the power to read any website — even the ones that block bots. An MCP server that returns clean Markdown and handles blocks automatically via residential proxies.
MIT -
A unified web extraction and stateful automation engine for AI. Replaces heavy testing frameworks with token-optimized browser control, deep research, and HITL.
go MIT ★ 71 -
Stealth browser for web scraping and AI agents: undetected Chrome over raw CDP, Cloudflare Turnstile, closed Shadow DOM & cross-origin iframes, HTML to Markdown, MCP server, LLM structured extraction (bring your own model). Puppeteer alternative.
npm MIT -
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, BrowserScan.
npm NOASSERTION ★ 2 -
A keyless web reader for AI agents. When a fetch hits a bot wall or a page that only renders in a browser, searchts tries a plain fetch, then a relay, then a real browser, and says plainly when it can't. MCP server, CLI, and Python library.
pypi MIT ★ 2 -
Give your AI agent a full Chrome workspace. 70 MCP tools powered by nodriver: browse, extract data, capture network traffic and inspect security. Reuse logins, run isolated browsers and restore your tabs. One-command setup for 15+ clients.
pypi MIT ★ 8 -
bestproxy4agents-mcpgithub.com/novadalabs/proxy4agentupdated this year
Residential proxy MCP server for AI agents — bypass Cloudflare/Akamai, geo-target 195+ countries, sticky sessions, Google search. Works with Claude, Cursor, Windsurf. Multi-provider: Novada, BrightData, Smartproxy, Oxylabs.
npm MIT -
The Web Access Layer for AI Agents. Bypass Cloudflare Turnstile & DataDome without 403 Forbidden. Extract clean Markdown, typed JSON & MCP tools for Cursor, Claude & LangChain.
MIT ★ 1 -
Local-first Chrome CDP reverse engineering & wire-level traffic MCP server, for Claude Code, Cursor, Codex, OpenCode, Gemini, AntiGravity, and Hermes Agent — zero DOM bloat, stealth bot bypass, 100% local
npm MIT