Skip to main content
Glama
YawLabs

@yawlabs/tailscale-mcp

by YawLabs
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Update ACL policy

tailscale_update_acl
DestructiveIdempotent

Update your Tailscale ACL policy safely by passing the full policy text and current ETag to prevent overwriting concurrent changes. Preserves formatting and comments.

Instructions

Update the ACL policy for your tailnet. Accepts the full policy as a string to preserve formatting, comments, and trailing commas (HuJSON). You MUST pass the ETag from tailscale_get_acl to prevent overwriting concurrent changes, or ts-default for the first write to a tailnet nobody has edited yet. Always get the current ACL first, make targeted edits to the text, and pass the full modified text back.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
etagYesThe ETag from tailscale_get_acl (quotes optional -- they are normalized). Required to prevent concurrent edit conflicts. For the FIRST write to a fresh tailnet you may pass `ts-default` instead: the update then succeeds only if the policy file is still Tailscale's untouched default.
policyYesThe full ACL policy text. Preserve existing formatting, comments, and structure. Only modify the specific parts that need to change.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.21.0
    • changedInput schema / properties / etag / description
      Previous value: -"The ETag from tailscale_get_acl. Required to prevent concurrent edit conflicts."New value: +"The ETag from tailscale_get_acl (quotes optional -- they are normalized). Required to prevent concurrent edit conflicts. For the FIRST write to a fresh tailnet you may pass `ts-default` instead: the update then succeeds only if the policy file is still Tailscale's untouched default."
  2. Changed1 schema field changedv0.18.0
    • addedInput schema / properties / etag / minLength
      Added value: +1
  3. First observedv0.13.3

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already indicate destructive/idempotent write behavior; the description adds critical context about preserving HuJSON formatting, preventing concurrent overwrites via ETag, and the first-write ts-default path. No contradiction with 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?

Three sentences with the core purpose front-loaded, followed by essential procedural constraints. Every sentence earns its place with no redundancy or filler.

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?

Together, the description and input schema fully cover the preconditions, the required parameters, and the expected payload format. With no output schema, return-value details are not necessary for an agent to invoke the tool correctly.

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?

Input schema coverage is 100% and both parameters are thoroughly described, including ETag normalization and ts-default semantics. The description reinforces the workflow and parameter usage but does not add new parameter-level details beyond the schema.

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 ('Update') and resource ('the ACL policy for your tailnet'), and clarifies the payload as the full policy string. This cleanly distinguishes it from sibling tools like tailscale_get_acl, tailscale_validate_acl, and tailscale_preview_acl.

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

Usage Guidelines5/5

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

Explicitly instructs the agent to always fetch the current ACL first, make targeted edits, and pass the full modified text back. It also names the required ETag and the ts-default exception for first writes, leaving no ambiguity about when and how to invoke the tool.

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