Tailscale

tailscale-mcp

An MCP server for Tailscale. The node it runs on is driven through the tailscale command-line interface; the tailnet behind it is driven through the control-plane REST API.

186 tools, one per verb, with real parameters and honest annotations. Tailscale's own JSON comes back unmodified, so anything you learned from Tailscale's documentation still applies. When something fails you get a fixed error code and a hint, not a wall of standard error.

Both surfaces are optional and neither is fatal. No tailscale binary means the tools that drive this node are not offered; no control-plane credential means the tools that drive the tailnet are not. tailscale-mcp diagnose says which of the two this machine has.

On macOS that binary is the tailscale shim the Tailscale application installs into /usr/local/bin. The executable inside the application bundle is not a substitute and is not accepted as one: run outside a login shell it starts the GUI rather than answering, so the local tools would be offered and then fail on every call.

Install

Release archives are on the releases page with a SHA256SUMS beside them: macOS and Linux on x86_64 and arm64, and Windows on x86_64.

Point a client at it

tailscale-mcp setup claude-code

prints the snippet for your client — claude-code, claude-desktop, vscode, cursor or zed — and says where it goes. It writes nothing: the snippet is yours to paste, and it leaves the credential out, for the reason in the next section.

Installed through npm there is nothing to install first, and the client can carry the settings:

{

"mcpServers": { "tailscale": { "command": "npx", "args": ["-y", "@tailscale-mcp/tailscale-mcp"], "env": { "TAILSCALE_MCP_ALLOW_WRITE": "true" } } } }

That much is enough to start it. Without a credential it offers the tools that drive this node and hides the ones that act on the tailnet, and tailscale-mcp diagnose says which of the two you have.

Authenticate

setup prints no credential of its own, because the file it prints into is one people paste into issues and chats without rereading. Adding one is a separate, deliberate step. Two shapes go in the env block above — an API access token:

"env": {

"TAILSCALE_API_KEY": "tskey-api-…", "TAILSCALE_MCP_ALLOW_WRITE": "true" }

or an OAuth client:

"env": {

"TAILSCALE_OAUTH_CLIENT_ID": "k123456CNTRL", "TAILSCALE_OAUTH_CLIENT_SECRET": "tskey-client-…", "TAILSCALE_MCP_ALLOW_WRITE": "true" }

The credentials table has the other shapes, including the JWT file for federated identity. Every tool is offered with either of these: the choice is not about what you can do with the server, which is why it is worth making on other grounds.

Prefer the OAuth client for anything you keep. The reason is what a client configuration *is*: a file somebody writes once and then forgets, holding a secret for as long as the tool is installed.

An API access token suits that badly on three counts. It belongs to a person and carries everything that person can do, so what leaks with the file is their whole account rather than the tools you turned on. It expires — which in a file nobody has looked at since they wrote it does not present as an expired credential, but as a server that has stopped working for no reason. And it is itself the bearer token, so the thing at rest is the thing that opens the door.

An OAuth client inverts each of those. It belongs to the tailnet, so it outlives whoever set it up and is revoked without touching that person's access. Its scopes narrow it to what the toolsets you enabled actually call. It does not expire on its own, and what sits in the file is not a key but the means of minting one — the token it hands this server lasts an hour, so a copy taken from a backup or a screen share is worth very little by the time it is used.

The API access token is what the control plane offers you first, and is the quicker thing to try this out with. It is worth replacing once the file is one you are going to keep.

Tiers and presets

Two independent dials decide what a session offers.

The tier is how dangerous a tool is allowed to be. Read tools change nothing and are always offered. Write tools change configuration that can be changed back. Destructive tools remove something or expose something in a way that is not simply undone — deleting a device, revoking a key, publishing a service to the internet. Read is always on; write and destructive are off until they are turned on, and a tool above the permitted tier is *not listed*, not refused when called.

The preset is how much surface area is offered at all. minimal is what an agent needs to answer questions and fix the common things; core adds the rest of everyday administration; full adds the tailnet-wide and irreversible corners. Two toolsets are in no preset and must be asked for by name: local-debug, which is Tailscale's own diagnostic surface, and local-passthrough, which is one tool that runs an arbitrary tailscale subcommand.

Adding --toolsets +local-debug,+local-passthrough to full reaches all 186.

Some destructive tools ask for one more thing: a confirm: true argument. Those are the ones that affect the whole tailnet, or that can cut this server off from the node or tailnet it is driving — logging the node out, deleting its own device, deploying a policy that locks the caller out. The server does not decide they are wrong; it makes the caller say it meant them.

• [docs/tools.md](docs/tools.md) — every tool, its tier and what it does. Generated from the code.
• [docs/configuration.md](docs/configuration.md) — every environment variable and flag, with defaults.
• [docs/errors.md](docs/errors.md) — every error code and what to do about it.

Resources, prompts and completions

Nine resources — eight fixed and one template addressed by device identifier — give a client the local node's status, preferences, netcheck report and tailnet lock state, and the tailnet's policy file, devices, DNS configuration and settings. They are read-only, they appear only when their surface is on, and there are no subscriptions.

Three prompts steer a sequence of tool calls: diagnose_connectivity, review_policy_change and audit_tailnet_access. They follow the same rule as the resources: each appears only when the surface it needs is on, and diagnose_connectivity, which reads from both, stops at the steps the session can actually take.

Of the four argument slots those two surfaces expose, three are completed, so a client can offer the values rather than leave them to be guessed: the device template's identifier, diagnose_connectivity's peer, and audit_tailnet_access's subject — which offers users, tags and devices, in that order, so that a tailnet of thousands of devices still shows its handful of users within the hundred values the protocol sends. The fourth, review_policy_change's goal, is a sentence about intent, and completing it would be inventing one. Every value offered is one the server will accept back — a device is offered by its MagicDNS name, never by a hostname two machines might share — and a source that cannot answer completes to nothing rather than to an error. The method is rate limited, as the specification asks, because each keystroke is a request.

Note that the protocol completes a prompt argument and a resource template variable, and nothing else: tool arguments cannot be completed, so this helps the four slots above and none of the 186 tools. Client support is uneven — Claude Code completes resource templates, VS Code completes both, and several clients do neither — so this is an improvement where it is read and inert everywhere else.

Transports

Stdio by default. --http serves Streamable HTTP instead, on 127.0.0.1:8449, behind a bearer token in TAILSCALE_MCP_HTTP_TOKEN, with host and origin allow-lists, a body limit, a per-address rate limit and an open health endpoint. Binding anywhere but loopback needs either that token or --http-no-auth said out loud.

Security

What the tiers do. A tool above the permitted tier is not in the tool list, so a caller cannot invoke it by guessing its name, and a model cannot be talked into one that was never offered. The default is read-only. confirm on top of the destructive tier is a second signal for the operations that are worth one. Secrets never reach an argument list, a log line or an error message; a minted key or invite URL is returned once, verbatim, and nothing here keeps a copy. Every tool result and every error goes through the same redaction on the way out.

What the tiers do not do. They are not an authorization system, and they are not a sandbox.

• A tier is a property of the *server*, not of the caller. Everyone talking to one server gets the same tools. If two callers should have different powers, run two servers.
• Permitting a tier permits every tool in it. There is no per-tool switch; --toolsets is the coarser dial for narrowing what a session can reach.
• The credential is the real boundary. A read-only OAuth client makes the tailnet write tools fail at the control plane whatever this server offers, and that is the boundary to lean on. Scope the credential, and use the tiers to stop honest mistakes.
• The local tools run as whoever runs this server. Tailscale's own operator check applies — commands refused to a non-operator are refused here, with needs_operator — but a server run as the operator can do what the operator can do.
• Read is not harmless. The read tier returns real network topology: node names, addresses, users, policy. Anything that can read the tool output can read that.

The server never escalates privileges. It does not use sudo, does not ask for elevation, and does not alter its own permissions or install anything. It runs the tailscale binary as the user it was started as and sends the control-plane credential it was given. Where Tailscale refuses because of who is asking, that refusal is passed through rather than worked around. Four tools do write files: three of them — a certificate, a Taildrop delivery, a metrics file — to the path the call names, and tailscale_configure_kubeconfig to the kubeconfig the client itself would edit. All four write as the user running the server, and so does tailscale_run, which is in no preset and, once asked for by name, can reach those same writes and anything else the tailscale binary does.

Over HTTP the defaults are the cautious ones — loopback, a token required, no browser origin allowed — and each of those is widened by a flag, deliberately.

Compared with the other Tailscale MCP servers

This server is a