- Spicrawl @officialspicrawl/mcpWeb scraping to Markdown and structured data, screenshots, batch jobs and browser sessions.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Zamery Browser @maemreyo/zamery-browserUse your existing Firefox and logged-in tabs, limited to tabs or groups you explicitly share.Not assessed yet.Runs on your machine, installed from npm.
- 6Frame Verify @bret1976/6frame-verifyPaid website acceptance testing for AI agents. Quick $3, Full $12, $100 credit pack. MCP + REST.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Auten @auten/mcpComputer use for Claude Code, Codex, Cursor or any MCP client: your computer + Android phone (beta)10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Crispy Profiling @edgeorgie/crispy-profilingDeterministic React render profiling: renders, wasted renders and their causes per component.Not assessed yet.Runs on your machine, installed from npm.
- Burrowbox @burrowbox/burrowboxPersistent Linux computers for AI agents: desktop, signed-in browser, vault, apps and shell.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- H/Ai Browser @festuscharles-n/hai-browserLet AI agents drive VS Code's built-in browser alongside you, with click-to-source.Not assessed yet.Runs on your machine, installed from npm.
- Delhaize receipts @shimabeigi/delhaize-mcpFetch your own Delhaize (Belgium) till receipts and weekly promotions with a headless browser.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- periscope @oskar-szulc/periscopeA real Safari-engine (WebKit) browser for agents on macOS: sessions, extraction, bot checks.Not assessed yet.Runs on your machine, installed from MCPB.
- X402 Scraper @ihen404/x402-scraper-apiProgrammatic web-scraping MCP server powered by x402 micro-transactions on Base.Not assessed yet.A remote server; no sign-in.
- Umd @avivkeller/umd-mcpMCP server exposing University of Maryland data16% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Menso @menso/mensoAI users run real tasks on your live site and show where they get stuck, with a replay of every stepNot assessed yet.A remote server; no sign-in.
- Relvato @relvato/relvatoWebsite monitoring: add sites, configure and run monitors, read health, review results, apply fixes.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Glamour @gratise/glamourBrowser-measured visual debugging and verification tools for coding agents.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- AgentLaunch @cracked-collective/agentlaunchPlan and run paced startup, SaaS and AI directory launches from your agent, in your own Chrome.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- Usable Browser Agent @savvy-tech-sphere/usable-browser-agentMCP server and Firefox add-on that let an AI agent drive your real, logged-in browser. Free tier.11% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Babelwrap @soulfir/babelwrap-mcpLet AI agents interact with any website through natural language instead of CSS selectors8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Readiness scorer — can an agent sign up to your SaaS? @agentwares/readiness-scorerProbe a signup URL you own and score whether an AI agent can sign up unaided.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- GhostQA @synctekllc/ghostqaAI personas navigate your web app in real browsers, find bugs and UX issues. No scripts needed.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- pxtree @alabsi91/pxtreeMeasures how a webpage actually renders and prints it as compact text for AI coding agents.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- CDP @dockndevai/mcp-cdpSafe-by-default MCP that drives an Electron/Chrome app over CDP: DOM, console, network, input.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- qarunbook @ifeanyiejindu/qarunbookShared app-testing runbook: read the plan, record results per platform, raise and fix issues.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Claw Post @daydreamnationtechlabs/clawpostAgent social posting via your logged-in Chrome. Remote MCP + OAuth. Not clawpost.dev.15% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- domscout @jkresearch8/domscoutdomscout browser API as MCP tools: screenshots, Markdown, structured data, page automation, crawls.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
