@yawlabs/tailscale-mcp

Diff ACL access

tailscale_diff_acl_access

Read-onlyIdempotent

Compare current and proposed Tailscale ACL policies per user to show who gains or loses access before applying a change.

Instructions

Answer 'who loses access?' before applying an ACL change. Compares the CURRENT policy against a proposed one and reports, per user, which destinations they gain and lose. Run this before tailscale_update_acl -- validate_acl only checks syntax and the policy's own tests block, so a policy with no tests validates clean while revoking everyone. LIMITS, all reported in the response rather than left to be discovered. It compares USER principals only, so a revocation that runs through a tag or group can show a clean diff, and an empty result is never proof a change is safe. Posture DEFINITION changes ARE detected: posture names are resolved to their rules, so tightening posture:corp shows as a change -- except when a preview omits the definitions map, where it falls back to comparing names. It costs two preview requests per user, so it checks the first 25 by default and stops starting new users after 60 seconds (a user whose previews are already in flight still finishes); either way it sets truncated, reports how many were skipped, and says which limit stopped it. Users whose preview fails are listed in failed and excluded from the compared count -- a failure is never reported as lost access, and if nothing could be compared the call fails rather than returning an empty diff.

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": {
      "policy": "<policy>"
    },
    "name": "tailscale_diff_acl_access"
  }
}

Input Schema

Name	Required	Description
`policy`	Yes	The proposed ACL policy text to compare against the current live policy
`principals`	No	Principals to check, as they appear in `loginName` from tailscale_list_users. That is often an email, but on a GitHub or SSO tailnet it is not (e.g. 'alice@github') -- pass the loginName verbatim rather than an address you assume. Omit to enumerate the tailnet's users automatically. Pass an explicit list to bound the request count, or to check specific users beyond the cap.
`maxPrincipals`	No	Maximum users to check (default 25). Each costs two preview requests. Raising this on a large tailnet can be slow and may hit rate limits.

Schema Changelog

Changes observed during successful MCP inspections.

Addedv0.19.1Sep 11, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations only declare readOnly/idempotent/non-destructive; the description adds substantial behavior: two preview requests per user, a default cap of 25, a 60-second budget that stops starting new users, and truncated/failed reporting. It also discloses a real correctness limit (user principals only, so tag/group revocations can show a clean diff) and failure semantics (nothing compared means the call fails rather than returning an empty diff).

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

Conciseness4/5

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

Front-loaded with the guiding question and the comparison behavior, then a clearly signposted LIMITS section. The limits sentence is long and packs several clauses (posture fallback, per-user cost, timeout, truncation, failure handling) into one dense run, costing a point on readability.

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?

There is no output schema, so the description carries the return contract itself and does: per-user gains/losses, `truncated`, skipped counts, the stopping limit, and `failed`. For a read-only diff tool whose main risk is a false 'safe' result, the caveats and failure mode are both covered.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is 3, but the description adds meaning the schema does not: the 60-second time budget interacts with how many principals can realistically be checked, and the reason to pass an explicit list ('to check specific users beyond the cap') is stated. It does not add format detail for the policy text itself, which is left to 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 and resource (compares CURRENT policy against a proposed one) and names the exact output shape ('per user, which destinations they gain and lose'). It explicitly distinguishes itself from tailscale_validate_acl and tailscale_update_acl, so an agent can route without opening the schema.

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?

Gives an explicit when: 'Run this before tailscale_update_acl'. It also gives the reason an alternative is insufficient ('validate_acl only checks syntax and the policy's own tests block... a policy with no tests validates clean while revoking everyone'), which is exactly the missing-alternative reasoning an agent needs.

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

Deploy Server