AI Access (MCP)
Let AI coding tools manage your servers over a local, token-secured MCP endpoint, with scoped permission tiers you can revoke at any time.
What AI Access does
AI Access lets AI coding tools "manage your servers over a local, token-secured MCP endpoint. Credentials never leave Server Compass." Open the AI MCP tab from the sidebar. The status pill reads Running ยท port {n}, Enabled, not running, or Disabled, and a toggle turns access on or off.
Create a token and choose tiers
The tab has Setup, Tools, and Activity. On Setup, create a token (the default name is Claude Code), choose which permission tiers it carries, optionally restrict it to an allowlist of servers, then copy the install snippet. Permission tiers:
- Read โ list servers, apps, logs, and templates; always safe and always on
- Operate โ start, stop, restart, and redeploy apps
- Deploy โ deploy templates, add servers, and manage domains, env vars, and secrets
- Danger โ destructive actions: delete apps or secrets and run raw SSH commands
Supported clients
AI Access generates install snippets for Claude Code, Codex CLI, Grok CLI, Gemini CLI, OpenCode, Cursor, Windsurf, Cline, and VS Code. The default endpoint is http://127.0.0.1:52700/mcp, the server registers as servercompass (short alias sc), and its tools appear to the AI as mcp__servercompass__*. Token secrets are stored in your operating system keychain, and you can revoke a token at any time.
Frequently Asked Questions
Can an AI agent delete my apps?
Only if you grant the token the "Danger" tier, which covers destructive actions like deleting apps or secrets and running raw SSH commands. A read-only token cannot change anything.
Ready to try Server Compass?
Download the app and deploy your first application in under 5 minutes.
Download Server Compass