- emisar @emisar/emisarLet AI operate servers without SSH. Choose actions, approve risky changes, and audit every step.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.337 GitHub stars.
- Remote Desktop Commander @desktopcommander/remote-desktop-commanderHosted MCP server connecting claude.ai, ChatGPT and other AI apps to your own computer14% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.154 GitHub stars.
- Local MCP @local-mcp/local-mcpMac & Windows: let ChatGPT, Claude & Cursor use your email, calendar, iMessage, Teams, files.19% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.66 GitHub stars.
- Herald @btouchard/heraldStop copy-pasting between Claude Chat and Claude Code.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.46 GitHub stars.
- Computer-Use Agents API @hcompai/hai-agentsRun and manage H Company's Computer-Use Agents from any MCP client.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.42 GitHub stars.
- Call Me @callmemcp/call-meYour AI rings your iPhone, speaks its question, and gets your spoken answer back as text.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.20 GitHub stars.
- hush @royashbrook/hushA secret store for AI agents: the agent never sees the plaintext.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.20 GitHub stars.
- Antrieb — Instant Clusters and Networks for AI Agents @antrieb/antriebValidates AI infra code on real VMs. Self-corrects until it works. No containers, no sandboxes.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.14 GitHub stars.
- SentinelX MCP @sentinelx/sentinelxOperate Linux, macOS and Windows from your LLM. Every action runs through an auditable allowlist.14% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.11 GitHub stars.
- Nucleus @eidetic-works/nucleusSovereign Agent OS — Persistent Memory, Governance & Compliance for AI Agents.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.5 GitHub stars.
- Ramus Android @ramus/androidDisposable cloud Android emulators for coding agents: run an APK or PR build, tap, type, screenshot.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.3 GitHub stars.
- Clousd @clousd-android/clousd-mcpA real Android phone in the cloud for MCP agents: observe the screen, act, reset to a saved state.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- AskYourStack @askyourstack/askyourstackLet Claude, ChatGPT or Cursor manage your servers, sites and SEO, with approvals for risky actions.16% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.1 GitHub stars.
- SudoWhizzy @sudowhizzy/sudowhizzyRenamed to AskYourStack: use com.askyourstack/askyourstack. Same service, now at askyourstack.com.13% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.1 GitHub stars.
- Runtime Cloud @withruntime/runtimeLinux microVM sandboxes for AI agents: run commands, files, processes, pause and wake.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.1 GitHub stars.
- ReMCP @getremcp/remcpSecurely control paired computers with ReMCP.15% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.1 GitHub stars.
- Parsee @parsee/parseeЦены, наличие, отзывы и СПП с Ozon и Wildberries — на компьютере продавца9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.1 GitHub stars.
- Clianythingharness @clauxel/clianythingharness-mcpA paid remote MCP for CLI tool MCP, built to return verdicts, receipts, usage logs, and audit-ready12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.1 GitHub stars.
- Node Command @huseyincig/nc-mcpRemote MCP server exposing your Node Command fleet (files, shell, processes, browser) to AI hosts.Not assessed yet.A remote server; it needs your API key.
- Keeploop @keeploop/keeploopMail, Calendar, Messages, Notes, Contacts, Slack on your Mac for AI. Remote needs Pro or free trial.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Phonebox @phonebox/phoneboxCloud Android phones for AI agents: create a phone, read the screen, tap, type, install APKs, park.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
Computer control MCP servers
A server here operates a computer or phone: desktop apps, operating system, shell commands.
Not here: browser-only automation.
116 remote1,095 localTagged by Odel's AI, which can make mistakes
Most popular in Computer control
By GitHub stars, at most two per publisher- Number 1: Mobilerun@droidrun/mobilerunControl real Android and iOS devices with LLM agents — tap, swipe, type, automate flows.13% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.9,571 GitHub stars.
- Number 2: Computer@pollinations/computerA private persistent computer: files and a bash shell that survive between runs.Not assessed yet.A remote server; it needs your API key.5,183 GitHub stars.
- Number 3: Unreal@smithery/chir24-unreal-mcpControl Unreal Engine to browse assets, import content, and manage levels and sequences. Automate…4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.911 GitHub stars.
