Skip to main content
Glama

Apply cluster manifest

apply_cluster_manifest
Destructive

Apply an ImportCluster YAML declaratively (the twin of ankra cluster apply): the cluster named in metadata.name is created if it does not exist, and every stack the manifest names is created or REPLACED by its definition there. Stacks the manifest does not name are left untouched. A member (add-on, manifest, application) of a named stack that the manifest no longer lists would be removed, so such a removal is refused, with nothing written, naming the members, unless confirmed_member_removals names each one or prune is true: a manifest exported before those members were added looks exactly the same. Read the current definition with export_cluster_iac first and validate with validate_cluster_manifest. Moving the cluster to a different GitOps repository or branch is refused until allow_repoint is true (and allow_repoint_destroying_data when PersistentVolumeClaims would be pruned). For one stack at a time prefer create_stack / update_stack.

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": {
      "manifest_yaml_base64": "<manifest_yaml_base64>",
      "cluster_id": "<cluster_id>"
    },
    "name": "apply_cluster_manifest"
  }
}

Input Schema

NameRequiredDescriptionDefault
pruneNoConfirm every removal this apply makes (default false). Only when the user said the manifest is the complete, current definition of the stacks it names; otherwise name the members in confirmed_member_removals.
cluster_idYesAnkra cluster id (UUID) the call targets. Discover ids with list_clusters.
allow_repointNoAcknowledge that the manifest moves the cluster to another GitOps repository or branch, rewriting the files there (default false).
manifest_yaml_base64YesThe ImportCluster YAML (kind: ImportCluster, metadata.name, spec.stacks and optionally spec.git_repository), base64-encoded, at most 2 MiB. Inline `manifest` and `configuration.values` blocks are accepted; file references (from_file) are refused.
confirmed_member_removalsNoMembers, as kind/name (kind addon, manifest or application), the user confirmed this apply may remove from the stacks it names because the manifest no longer lists them. Send only after the apply was refused naming them and the user agreed to each.
allow_repoint_destroying_dataNoThe second acknowledgement required when the cluster holds PersistentVolumeClaims the repoint would prune (default false).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / confirmed_member_removals
      Added value: +{
      +  "description": "Members, as kind/name (kind addon, manifest or application), the user confirmed this apply may remove from the stacks it names because the manifest no longer lists them. Send only after the apply was refused naming them and the user agreed to each.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / prune
      Added value: +{
      +  "description": "Confirm every removal this apply makes (default false). Only when the user said the manifest is the complete, current definition of the stacks it names; otherwise name the members in confirmed_member_removals.",
      +  "type": "boolean"
      +}
  2. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations only declare destructive/non-idempotent/non-readonly; the description goes well beyond them by explaining exactly what is destroyed (unlisted members of named stacks; PVCs on a repoint), that refusals write nothing, and which acknowledgement flags unlock each path. It also explains why the guard exists (an older export looks identical), which is the kind of reasoning an agent needs to avoid a bad confirmation.

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?

Well front-loaded: what it does, then untouched-stacks scope, then refusal semantics, then prerequisites, then alternatives. It is dense and runs long with stacked colon clauses, so it is slightly harder to scan than it needs to be, but no sentence is filler.

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 destructive, non-idempotent cluster-wide apply with no output schema, the description covers scope, refusal behavior, prerequisites and escalation paths thoroughly. The only real gap is what a successful apply returns or how progress is observed (e.g. whether an execution must be waited on), which an agent may still need to guess.

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; the description earns above that by explaining the interplay between prune and confirmed_member_removals (prune confirms every removal, per-member confirmation is the narrower path) and the two-stage repoint acknowledgement including the PVC/data-loss condition. It does not, however, add anything about manifest encoding or size limits beyond what the schema already states.

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 (apply an ImportCluster YAML declaratively) and immediately defines the create-if-missing / create-or-REPLACE semantics per named stack. It explicitly distinguishes itself from siblings (create_stack / update_stack for single stacks, export_cluster_iac and validate_cluster_manifest as companions), so an agent can route correctly without opening a 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 workflow (read with export_cluster_iac first, validate with validate_cluster_manifest) and an explicit alternative (prefer create_stack / update_stack for one stack at a time). It also names the conditions under which the call is refused and what must be supplied to proceed, which is usage guidance of the strongest kind.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.