Skip to main content
Glama
@yawlabs/tailscale-mcp

@yawlabs/tailscale-mcp

by YawLabs

Set devices authorized (bulk)

tailscale_set_devices_authorized
DestructiveIdempotent

Authorize or deauthorize multiple Tailscale devices in one call, returning per-device successes and failures so you can batch-enroll CI hosts or revoke flagged devices without losing partial results.

Instructions

Authorize or deauthorize multiple devices in one call. Each device's POST runs in parallel; per-device errors are returned alongside the successes so a partial failure doesn't lose the work that succeeded. On partial failure the call still returns success (ok) with data: { authorized, succeeded, failed } -- inspect data.failed for the per-device errors. POSTs are never retried, so on a large batch a rate-limited device lands in data.failed with status 429: re-call with just those ids, or set TAILSCALE_MAX_CONCURRENT to cap requests in flight. Common use: authorize a batch of newly-enrolled CI hosts, or deauthorize a group of devices flagged by a security review.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "deviceIds": "<deviceIds>",
      "authorized": "<authorized>"
    },
    "name": "tailscale_set_devices_authorized"
  }
}

Input Schema

NameRequiredDescriptionDefault
deviceIdsYesDevice IDs to update (nodeIds preferred; legacy numeric ids also work)
authorizedYestrue to authorize, false to deauthorize

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.21.0
    • changedInput schema / properties / deviceIds / description
      Previous value: -"Device IDs to update"New value: +"Device IDs to update (nodeIds preferred; legacy numeric ids also work)"
  2. First observedv0.13.3

TDQS

A4.5/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the annotations (destructiveHint, idempotentHint) by disclosing parallel POST execution, the partial-failure contract where the call still returns ok with data.failed, that POSTs are never retried, and the 429 failure mode plus the TAILSCALE_MAX_CONCURRENT mitigation. This is precisely the failure semantics an agent cannot infer from structured fields, and it is consistent with the declared annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Five sentences, each carrying distinct information: purpose, execution model, return contract, failure/recovery behavior, and use cases. It is front-loaded with the action and scope, and nothing repeats what the schema or annotations already say.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly takes on the burden of explaining the return shape ({ authorized, succeeded, failed }) and the surprising success-on-partial-failure behavior. For a 2-parameter bulk mutation with annotations, nothing material an agent needs is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so deviceIds, the nodeId preference, and the authorized boolean are already fully documented. The description adds only the operational note about re-calling with failed ids; it introduces no new meaning for the parameters themselves, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Authorize or deauthorize multiple devices') and makes the bulk scope explicit in the first sentence ('in one call'), which is exactly what separates it from the single-device siblings tailscale_authorize_device and tailscale_deauthorize_device.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives two concrete usage scenarios (batch-authorizing newly enrolled CI hosts, deauthorizing security-flagged devices) and explains the recovery path for rate-limited batches. It never explicitly names the single-device sibling as the alternative for one-off updates, so the when-not guidance is implied rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools