Skip to main content
Glama
YawLabs

@yawlabs/tailscale-mcp

by YawLabs
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Set split DNS

tailscale_set_split_dns
DestructiveIdempotent

Assign domains to specific nameservers in your tailnet's DNS. Replaces the whole split DNS config: domains left out are removed, and null clears a domain's nameservers.

Instructions

Set split DNS configuration. Maps domains to specific nameservers. Replaces the entire split DNS configuration: a domain you leave out is removed, and an empty object clears every domain. Per the API reference, setting a domain to null clears that domain's nameservers.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
splitDnsYesMap of domain to nameserver list, or to null to clear that domain (e.g. { "corp.example.com": ["10.0.0.1"], "old.example.com": null })

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.21.0
    • addedInput schema / properties / splitDns / additionalProperties / anyOf
      Added value: +[
+  {
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  },
+  {
+    "type": "null"
+  }
+]
    • removedInput schema / properties / splitDns / additionalProperties / items
      Removed value: -{
-  "type": "string"
-}
    • removedInput schema / properties / splitDns / additionalProperties / type
      Removed value: -"array"
    • changedInput schema / properties / splitDns / description
      Previous value: -"Map of domain to nameserver list (e.g. { \"corp.example.com\": [\"10.0.0.1\"], \"internal.dev\": [\"10.0.0.2\"] })"New value: +"Map of domain to nameserver list, or to null to clear that domain (e.g. { \"corp.example.com\": [\"10.0.0.1\"], \"old.example.com\": null })"
  2. First observedv0.13.3

TDQS

A4.8/5.0
Behavior5/5

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

Even though destructiveHint and idempotentHint are already present in annotations, the description goes further by explaining exactly what gets destroyed: the entire split DNS configuration, omitted domains, and empty-object clearing behavior. It also discloses that setting a domain to null clears that domain's nameservers, which is valuable behavioral context beyond the structured 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 concise sentences, each carrying essential information. The core purpose is front-loaded, and the destructive/clearing semantics follow logically. No filler or repetition of the schema's example.

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?

For a one-parameter mutation tool with no output schema, the description covers everything needed to call it correctly: what it does, the full-replacement semantics, the clearing behavior, and the null convention. The annotations cover idempotency and destructiveness, so no critical behavioral information is missing.

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

Parameters5/5

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

The schema already documents the splitDns parameter well and provides an example, so baseline is high. The description adds substantial extra meaning beyond the schema: omitted domains are removed, an empty object clears every domain, and null clears a single domain's nameservers. These are exactly the nontrivial semantics an agent needs to invoke the parameter correctly.

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?

The description names a specific verb and resource ('Set split DNS configuration') and immediately defines the distinguishing behavior: it replaces the entire split DNS configuration, not just the supplied entries. This makes it clearly distinct from get_split_dns and from a partial-update sibling such as tailscale_update_split_dns.

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?

The description gives clear context for when to use the tool: when you want to set split DNS with full-replacement semantics. It also explains consequences ('a domain you leave out is removed, and an empty object clears every domain'), which is important usage guidance. It does not explicitly name alternatives or state 'use X for partial updates,' but the replacement wording already implies the boundary.

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