- Drengr @drengr/serverEyes and hands for AI agents on Android and iOS devices.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- 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.
- EQVPS — VPS and code sandboxes for AI agents @poiuyhje/eqvpsNo-KYC VPS + per-second code sandboxes AI agents run over MCP — 75 tools, SDK, pay BTC/XMR/USDC/USDT13% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- File Smith @smithery/bhushangitfull-file-mcp-smithManage files and folders directly from your workspace. Read and write files, list directories, cre…9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Shellway @getshellway/shellwayWork on your own computers from Claude or ChatGPT: run commands, edit and search files.14% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Celesto Cloud Computers @celesto/mcpHosted MCP for Celesto cloud computers: create, exec, ports, start/stop/delete.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Emuluxe @emuluxe/mcp-serverLaunch and verify high-fidelity mobile simulations from an AI agent.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- autoMessage @automessage/mcpSend and read iMessages from your own Mac and Apple ID — drafts, history and contacts.13% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- RelayDesk @lakshay-24/relaydeskConnect AI assistants to explicitly paired computers, servers, and VMs for permitted remote actions.18% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- 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.
- Hardline Phone @hardlinephone/mcpDedicated remote-access US-based Android phones with a real US number. Pay crypto, control via MCP.35% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- 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.
- NoMac @nomac/nomacCloud macOS with Xcode for AI agents: run commands, build, test and ship iOS apps.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- BCD — Bridge Control Delegate @snack-wrap/bcdUse your Mac, Windows or Linux computer from ChatGPT, Claude or Codex: files, commands, documents.13% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Device Manager @vladkarpman/device-manager-mcpMCP server for fast Android device interaction with scrcpy acceleration (~50ms latency).5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Screen Buffer @vladkarpman/screen-buffer-mcpMCP server for fast Android screenshots via scrcpy frame buffer (~50ms latency).4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Camacho @sanchirico/camacho-mcpPersistent tmux terminal for AI agents — real-time spectating, SSH host-group dispatch.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- NIRA REPL MCP @pachote/nira-replSecure code execution sandbox for Claude — run Python, JavaScript, and shell commands10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- mpop @meshpop/mpopServer fleet management MCP — monitor, deploy, and manage distributed Linux servers5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- vssh @meshpop/vsshSSH tunnel and remote server management MCP — execute commands, transfer files, manage7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- Filesystem @infoinlet-marketplace/mcp-filesystemHardened filesystem for AI agents — jailed root, read-only default, traversal/symlink-safe.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Cockpit @daleweaver1981/cockpit-mcp40 AI prompts + self-hosted ops dashboard for homelab and small-team sysadmins7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Verirun @baopeak/verirunExecution-grounded verification for AI coding agents on Windows: evidence, not agent claims.12% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
