spinnaker-mcp

Overview Schema Source Related Servers Discussions Admin

Find target server group

get_target_server_group

Read-onlyIdempotent

Retrieves one server group from a Spinnaker cluster using a target selector such as current, previous, oldest, or largest, helping identify live deployments or plan rollbacks.

Instructions

Get one server group of a cluster by a target selector instead of its name: current (or newest), previous (or ancestor), oldest, largest, or fail (errors unless exactly one server group exists). Use this for rollback planning or to find what is live now. Returns JSON with the matched server group.

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": {
      "application": "<application>",
      "account": "<account>",
      "cluster_name": "<cluster_name>",
      "cloud_provider": "<cloud_provider>",
      "scope": "<scope>",
      "target": "<target>"
    },
    "name": "get_target_server_group"
  }
}

Input Schema

Name	Required	Description
`scope`	Yes	Scope for target lookup (e.g. a region like us-east-1)
`target`	Yes	Target selector, as Clouddriver names it: current and newest are the latest server group, previous and ancestor the one before it
`account`	Yes	Spinnaker account name
`application`	Yes	Application name as registered in Spinnaker
`cluster_name`	Yes	Cluster name as shown in the Spinnaker UI
`cloud_provider`	Yes	Cloud provider (e.g. aws, gce, kubernetes)

Output Schema

Name	Required	Description	Default
`count`	No	Number of records in items.
`items`	No	The records, when Gate answered with a list.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv0.4.1Nov 1, 2026

changedInput schema / properties / target / description

Previous value: -"Target type: newest, oldest, largest, smallest, or ancestor"New value: +"Target selector, as Clouddriver names it: current and newest are the latest server group, previous and ancestor the one before it"

addedInput schema / properties / target / enum

Added value: +[
+  "current",
+  "newest",
+  "previous",
+  "ancestor",
+  "oldest",
+  "largest",
+  "fail"
+]

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "description": "The Gate response. A JSON object from Gate comes back as is; a JSON array comes back as {items, count}.",
+  "properties": {
+    "count": {
+      "description": "Number of records in items.",
+      "minimum": 0,
+      "type": "integer"
+    },
+    "items": {
+      "description": "The records, when Gate answered with a list.",
+      "type": "array"
+    }
+  },
+  "type": "object"
+}

Changed1 schema field changedv0.3.4Oct 5, 2026
- changedInput schema / properties / cluster_name / description
```
Previous value: -"Cluster name"New value: +"Cluster name as shown in the Spinnaker UI"
```
First observedv0.1.0Apr 23, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive), so the description usefully spends its budget elsewhere: it discloses error behavior ("fail" errors unless exactly one server group exists) and the return type (JSON with the matched server group). It does not say what happens when a non-fail selector matches nothing, which is the remaining behavioral gap.

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?

A single front-loaded sentence that moves from identity to selector semantics to use case to return type, with no filler or redundant restatement of the tool name.

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 lookup with an output schema and fully documented parameters, the definition covers purpose, usage, selector semantics and return type. The only material omission is empty-match behavior for selectors other than "fail".

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 the baseline is 3, and the description still adds non-schema meaning for the least obvious enum value: "fail" errors unless exactly one server group exists. The current/newest and previous/ancestor gloss largely restates the schema's own target description, limiting the lift to a modest increment above baseline.

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 (get one server group of a cluster) plus the distinguishing mechanism: lookup by target selector rather than by name. An agent can tell this apart from list_server_groups or get_cluster from the first clause alone.

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?

"Use this for rollback planning or to find what is live now" gives concrete selection contexts and the phrase "instead of its name" implicitly contrasts it with a name-based lookup. It stops short of explicit when-not-to-use guidance or naming a specific alternative tool.

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