Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
Looks like a goal we have a starting path for: I want to build an AI agent
-
donsetch
Agents & frameworksWeb fetch, search, and crawl for AI agents. Built from scratch in Rust. No keys, no accounts. AGPL v3.
git clone https://github.com/dondai44423/donsetch.git -
stealth-browser-mcp
MCP serversStealth browser automation for AI agents over MCP and the Chrome DevTools Protocol: navigation, network hooks, DOM extraction, and pixel-accurate UI cloning.
git clone https://github.com/vibheksoni/stealth-browser-mcp.git -
mcp-stealth-chrome
MCP serversStealth 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.
git clone https://github.com/RobithYusuf/mcp-stealth-chrome.git -
invisible_dots
SkillsOpen-source, self-hosted alternative to OpenAI Dots, Grok Bot. Built to be undetectable by anti-bot systems.
git clone https://github.com/feder-cr/invisible_dots.git -
Svipall
MCP serversRead any page past its anti-bot wall, crawl sites, search without an API key, solve captchas locally
svipall@2.1.0 -
mcp-camoufox
MCP serversMCP server for stealth browser automation via Camoufox - 100+ tools, npx install, anti-bot stealth
git clone https://github.com/RobithYusuf/mcp-camoufox.git -
ZenRows
Public APIsWeb Scraping API that bypasses anti-bot solutions while offering JS rendering, and rotating proxies
-
SolveHub
MCP serversCAPTCHA and anti-bot solving for Turnstile, DataDome, Akamai, PerimeterX and Imperva.
ghcr.io/seencxy/solvehub-mcp:0.1.0 -
skills
SkillsOfficial Legba skill. Gets agents onto sites that block cloud traffic, escalating from plain fetch to hardened browsers only when needed. Flat pricing, no bandwidth meter.
git clone https://github.com/legba-app/skills.git -
playwright-stealth
MCP serversBrowser automation using Playwright with optional stealth mode to bypass anti-bot protection.
playwright-stealth-mcp-server@0.2.3 -
pulse-fetch
MCP serversMCP server for fetching web resources with content extraction and anti-bot bypass.
@pulsemcp/pulse-fetch@0.3.3 -
proxyclaw
MCP serversResidential proxy MCP server. 175M+ IPs in 195+ countries with anti-bot bypass.
proxyclaw-mcp-server@1.0.4 -
neo-vision
MCP serversSpatial DOM maps for AI agent browser navigation with anti-bot stealth.
neo-vision@0.2.2 -
ShadowCrawl
MCP serversRust MCP stealth scraper: anti-bot search/scrape with CDP fallback + HITL non-robot.
-
proxy4agents-mcp
MCP serversResidential proxy MCP for AI agents — geo-targeting, sticky sessions, anti-bot bypass.
bestproxy4agents-mcp@1.7.0 -
proxy-veil
MCP serversResidential proxy MCP server for AI agents — geo-targeting, sticky sessions, anti-bot bypass.
proxy-veil@1.5.4 -
PyreCrawl
MCP serversWeb scraping + research toolkit for AI agents: scrape, crawl, monitor URLs with anti-bot bypass.
pyrecrawl@0.8.1 -
BrowserSolver
MCP serversUnlock, render, crawl and screenshot any website — anti-bot bypass and technology detection through…
@browsersolver/mcp@0.1.0 -
Spider Cloud
MCP serversCrawl, scrape, search the web, and automate browsers at scale with anti-bot bypass.
-
scrapeunblocker-dfsswg
MCP serversScrapeUnblocker: ScrapeUnblocker allows to bypass anti-bot services and scrape the full page source.
-
pulse-fetch
MCP serversMCP server that extracts clean, structured content from web pages with anti-bot bypass capabilities.
@pulsemcp/pulse-fetch@0.2.14 -
MCP Browser
MCP serversBrowser automation using the user's Chromium session — JS execution, auth, and anti-bot support.
mcpbrowser@1.10.110 -
fetchmcp
MCP serversDrop-in fetch MCP: clean Markdown from any URL, with JS rendering and anti-bot.
@labtoolsstudio/fetchmcp@0.1.1 -
environmental-esg-mcp
MCP servers⚠️ DEPRECATED — G2's Cloudflare anti-bot defeats free scraping. Not commercially viable without paid
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.