- Familiar @dominion525/familiar-mcpMCP server that drives the user's real macOS Chrome via AppleScript. 32 tools.10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Chrome DevTools MCP @dinesh-nalla-se/chrome-devtools-mcpMCP server for Chrome DevTools5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Playwright @dinesh-nalla-se/playwright-mcpPlaywright Tools for MCP5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Codify @cybairfly/codify-mcpEasily create reusable automation tools from casual browser actions using Apify Agent7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Compass @chrischall/compass-mcpCompass real-estate for Claude — search, property details, photos, price history, compare14% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- BabelWrap @babelwrap/babelwrap-mcpMCP server for BabelWrap — give AI agents web browsing superpowers.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- PWA Debug Layer @aryanduntley/pwa-debug-layerDebug PWAs in your real browser via MCP: service-worker, cache, installability & framework state.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- ZenLink MCP @jayquan-mccleary/zenlink-mcpBrowser automation for MCP clients via Zen Browser. Parallel multi-tab, content extraction.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Gorgon Scout @gorgon-cyber/gorgon-scoutRun AI-driven web-app and API security scans (DAST) from Claude or any MCP agent. Windows.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- Browsegrab @arknill/browsegrabToken-efficient browser agent for local LLMs. Playwright + accessibility tree + MarkGrab.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Snapgrab @arknill/snapgrabURL to screenshot with metadata. Python MCP server. Claude Vision optimized.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Val @nyx-intelligence/valQA agent for vibecoded apps. Real browser checks, your AI fixes them. Ship to green.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Uplink @uplink/uplinkAutomate a real, logged-in browser on your own device — no stored credentials, no bot detection.22% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Nocticas @nocticas/nocticasBrowser QA agent that won't return a false green: verified PASS/FAIL + access-control probing.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- RobotActions — AI-Driven Mobile + Web Test Automation @krishtoautomate/robotactionsDrive real Android & iOS devices and web browsers from natural language for mobile + web QA.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- Playwritermcp @clauxel/playwritermcp-mcpA paid remote MCP for AI agent browser MCP session, built to return verdicts, receipts, usage logs,11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Anchor Browser @anchorbrowser/anchor-browserCloud browsers for AI agents: get past bot detection, sign in with MFA, run web tasks at scale.21% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- SnapSweep @snapsweep/snapsweepRead-only web QA agent: scans a site in a real browser and returns evidence-backed findings10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Frontlatch @frontlatch/gatewayRead any website's pages and action map, and find businesses an agent can act on.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Noxgild @noxgild/noxgildSecure AI access to Windows, macOS, Linux computers and a hosted Cloud Browser.15% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Shardflux @shardflux/mcpPersistent cloud workspaces for AI agents: run commands, edit files, use git and a browser.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- UXMachine @qtorb/uxmachineMeasures your site in a real browser and returns verifiable observations, with evidence and limits.Not assessed yet.A remote server; you sign in with your account.
- Connections @lunarwerx/connectionsAWS, GitHub and connected services from your agent, no keys to paste, plus local shell and browser.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- oassis — web scraping, crawling and browser control for AI agents @oassis/scraper-crawlerScrape to markdown, map and crawl sites, drive a real browser. Pay per call, no API key, no signup.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
