- opencode subagents @sebstaq/opencode-subagent-mcpRun Claude Code subagents on cheaper opencode models (DeepSeek, opencode Go) with native parity.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- agentchan @damejeras/agentchanLets one coding agent talk to another: Claude Code, Codex or Grok16% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from cargo.
- Mac Mail MCP @wagamama/mac-mail-mcpMac Mail MCP server with full-coverage FTS5 body search for local Apple Mail.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Os Automation Mcp @varvararatta/os-automation-mcpMCP server for OS Automation9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Mail @honeycrisp-suite/mailApple Mail over MCP: fenced reads, draft-only writing, human-gated actions, audited with undo.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Cron Self Heal @dailyaiagents-cpu/cron-self-healWatcher — surfaces crons in error state16% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- Gateway Pulse @dailyaiagents-cpu/gateway-pulseProbe Hermes/OpenClaw/Paperclip/Obsidian28% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- Dock Timelapse @bcldvd/dock-timelapseRecord how your macOS Dock evolves and render Apple-style timelapse videos of it.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- TinkyVision @agewellepm/tinkyvisionScreen observation, OCR and permission-controlled app input over MCP for Apple silicon Macs.10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- Gateway Pulse @usedailyai/gateway-pulseProbe Hermes/OpenClaw/Paperclip/Obsidian29% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- Termix @sujirodev/termix-mcpManage hosts, snippets, dashboard, metrics and audit of a self-hosted Termix (SSH/RDP/VNC manager)5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Portveil @roybogs/portveil-mcpMCP server for Portveil: let AI assistants see your devices and move them between VPN locations.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Task tracking (sessions, ETA, dashboard) @amineutron/mcp-trackingTrack long-running tasks in real time: sessions, steps, speed, ETA, HTTP API and TUI dashboard.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- kiriya @satpaingoo/kiriyaDeveloper tools for files, git, ports, processes and more, the same on Windows, Linux and macOS4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- ParallelSandbox @parallelsandbox/parallelsandboxRemote Linux boxes for coding agents: Docker, a browser, screenshots, logs, human takeover.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Hermes Agent @woonyong-choi/hermes-agent-mcpOperate a local Hermes Agent install over stdio: tasks, cron, config, gateway, doctor. No network.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- MarsDawn @southern-light/marsdawnExport Markdown to PDF and open it in the MarsDawn app on macOS, with the marsdawn CLI.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- JevSim @huaaudio/jevsimRun verified iOS and Android UI workflows in one agent tool call with Jev.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Ganado Bridge @cynarax/bridge-by-ganadoLocal Mac tools plus outbound pairing for the Ganado Bridge managed relay preview.10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- vaultguard @ashishrao-4/vaultguardAI agents use your Obsidian secrets by name — values never reach their context.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Homeport @capitalx/homeportApple Calendar, Reminders, Contacts, Notes, Messages and Shortcuts for AI, over Tailscale4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- VPS Guardian @murzirius/vps-guardian-mcpSecure SSH bridge for AI agents to observe and safely administer Linux VPSs.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Morfiade @morfiade-app/morfiade-mcpManage local Chrome profiles on Windows: own cookies, sessions and proxy per profile.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- ultranix-mcp @jxoesneon/ultranix-mcpSecure Linux desktop automation - input, screen/OCR/vision, AT-SPI2 UI tree, window, clipboard7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.
