Skip to main content
Glama
YawLabs

@yawlabs/tailscale-mcp

by YawLabs
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Get audit log

tailscale_get_audit_log
Read-onlyIdempotent

Retrieve tailnet audit logs to see who changed what and when, with optional filters for actor, target, or event. Ideal for troubleshooting and compliance.

Instructions

Get the tailnet audit/configuration log. Shows who changed what and when -- useful for troubleshooting and compliance. Optional actor, target and event filters narrow the query server-side, so a targeted question doesn't have to pull the whole window.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
endNoEnd time in RFC3339 format. Optional: when omitted the tool sends the current time, which Tailscale's API requires.
actorNoServer-side filter: one exact actor ID, or '~text' to wildcard-match a login or display name (e.g. '~bob'). One value per call -- how the API reads a repeated filter key is not verified yet.
eventNoServer-side filter: one event type from Tailscale's audit event list, e.g. 'TAILNET.UPDATE.ACL', 'TAILNET.UPDATE.DNS_CONFIG', 'NODE.CREATE', 'NODE.DELETE', 'API_KEY.CREATE', 'USER.UPDATE.USER_ROLE', 'WEBHOOK_ENDPOINT.CREATE'. Not a closed set -- the list keeps growing. One value per call, as for actor.
startYesStart time in RFC3339 format (e.g. '2026-04-01T00:00:00Z'). Required.
targetNoServer-side filter: one string, matched against any part of any of an entry's targets (ID or name). One value per call, as for actor.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.21.0
    • addedInput schema / properties / actor
      Added value: +{
+  "description": "Server-side filter: one exact actor ID, or '~text' to wildcard-match a login or display name (e.g. '~bob'). One value per call -- how the API reads a repeated filter key is not verified yet.",
+  "items": {
+    "minLength": 1,
+    "type": "string"
+  },
+  "maxItems": 1,
+  "type": "array"
+}
    • changedInput schema / properties / end / description
      Previous value: -"End time in RFC3339 format. Defaults to now."New value: +"End time in RFC3339 format. Optional: when omitted the tool sends the current time, which Tailscale's API requires."
    • addedInput schema / properties / event
      Added value: +{
+  "description": "Server-side filter: one event type from Tailscale's audit event list, e.g. 'TAILNET.UPDATE.ACL', 'TAILNET.UPDATE.DNS_CONFIG', 'NODE.CREATE', 'NODE.DELETE', 'API_KEY.CREATE', 'USER.UPDATE.USER_ROLE', 'WEBHOOK_ENDPOINT.CREATE'. Not a closed set -- the list keeps growing. One value per call, as for actor.",
+  "items": {
+    "minLength": 1,
+    "type": "string"
+  },
+  "maxItems": 1,
+  "type": "array"
+}
    • addedInput schema / properties / target
      Added value: +{
+  "description": "Server-side filter: one string, matched against any part of any of an entry's targets (ID or name). One value per call, as for actor.",
+  "items": {
+    "minLength": 1,
+    "type": "string"
+  },
+  "maxItems": 1,
+  "type": "array"
+}
  2. First observedv0.13.3

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering safety. The description adds behavioral context by explaining that filters operate server-side and that the log shows change history, which is useful for selecting the tool. It doesn't mention pagination or response format, but the annotation coverage lowers the bar, and the added context earns a 4.

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?

The description is two sentences, front-loads the core purpose, and adds a concise note about filters. Every sentence earns its place with no redundancy or fluff.

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

Completeness4/5

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

For a read-only get operation with a rich input schema and safety annotations, the description covers the main purpose, content, and filter behavior. It doesn't describe the return format, but the absence of an output schema and the tool's straightforward nature make this acceptable. Overall, it's complete enough for an agent to call 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?

Schema description coverage is 100%, with each parameter (start, end, actor, event, target) having detailed descriptions. The description only reiterates that filters exist and narrow queries server-side, adding marginal value over the schema. Baseline of 3 is appropriate for high coverage.

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

Purpose4/5

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

The description clearly states the tool retrieves the tailnet audit/configuration log and explains what it shows ('who changed what and when'). It's a specific verb+resource, and the purpose is unambiguous. It doesn't explicitly differentiate from siblings like tailscale_get_network_flow_logs, but the resource is distinct enough that the intent is clear.

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

Usage Guidelines3/5

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

The description provides context on when to use the tool (troubleshooting, compliance) and hints at using filters for targeted queries. However, it doesn't explicitly state when not to use it or mention alternatives like network flow logs. Usage guidance is implied rather than explicit.

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