Tailscale MCP Server

Tailscale MCP server for managing your tailnet from AI assistants. That is what the tailscale mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

One click adds this to your local Yaw MCP config so it's available in every Yaw Terminal session. Or install manually below.

• Typed tool surface, not string parsing. — Every tool has a Zod-validated input schema and a structured response. No brittle tailscale status --json | jq pipelines that break when the schema evolves
• Safe-by-default writes. — Every tool declares readOnlyHint / destructiveHint / idempotentHint so clients can skip confirmation on reads and require it on mutations. A skill that shells out to the CLI can't express that

The tools it exposes

The server publishes 14 tools. What each one is for:

• tailscale_status — Verify API connection, see tailnet info and device count
• tailscale_list_devices — List all devices with status, IPs, OS, and last seen
• tailscale_get_device — Get detailed info for a specific device
• tailscale_authorize_device — Authorize a pending device
• tailscale_deauthorize_device — Deauthorize a device
• tailscale_set_devices_authorized — Authorize/deauthorize many devices in one call (parallel, per-id error reporting)
• tailscale_delete_device — Remove a device from the tailnet
• tailscale_rename_device — Rename a device
• tailscale_expire_device — Expire a device's key, forcing re-authentication
• tailscale_get_device_routes — Get advertised and enabled subnet routes
• tailscale_set_device_routes — Enable or disable subnet routes
• tailscale_get_device_posture_attributes — Get all posture attributes for a device

Getting it running

Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.

What it needs from you

Configuration is passed through the environment: TAILSCALE_API_KEY, TAILSCALE_PROFILE, TAILSCALE_TOOLS, TAILSCALE_READONLY, TAILSCALE_OAUTH_CLIENT_ID, TAILSCALE_OAUTH_CLIENT_SECRET. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

How it compares

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Tailscale's toolset — tailscale_status, tailscale_list_devices, tailscale_get_device and 11 more — is a fair guide to whether it matches your workflow. It is maintained by jeffyaw; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Tailscale's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Things to watch

• Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
• With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Tailscale.
• Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
• Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.