Skip to main content
Glama

Ankra

by ai.ankra
OverviewDiscussionsAdmin

create_upcloud_cluster

Destructive

Create and provision a new Kubernetes cluster on UpCloud. Requires an UpCloud API credential, SSH key credential, and a zone. The cluster will begin provisioning immediately after creation. Use list_provider_credentials to find credential IDs and list_instance_types for plan sizes.

Input Schema

NameRequiredDescriptionDefault
nameYesCluster name. Must be unique within the organisation.
zoneYesUpCloud zone (e.g., 'de-fra1', 'fi-hel1', 'nl-ams1', 'us-chi1').
zonesNoZone pool for a multi-zone cluster; must include 'zone' (the primary). Needs at least 3 zones and 3 control planes; the nodes are joined by a platform-managed WireGuard mesh. Omit for a single-zone cluster.
descriptionNoOptional cluster description.
worker_planNoUpCloud plan for worker nodes. Default: 'PREMIUM-2xCPU-4GB'.
bastion_planNoUpCloud plan for the bastion host. Default: 'STARTER-1xCPU-1GB'.
distributionNoKubernetes distribution. Default: 'kubeadm' (vanilla upstream Kubernetes with Cilium). 'k3s' is the lightweight alternative.
gateway_planNoUpCloud NAT gateway plan every node's outbound internet runs through. Default: 'standard' (500 Mbps, two servers). A plan with server_number 1 ('development', 'essentials') cuts all cluster egress while UpCloud rebuilds its one server; two-server plans fail over. Get the plans from list_upcloud_options (gateway_plans).
network_modeNoDerived when omitted: 'wireguard_mesh' for a multi-zone pool, 'private_network' otherwise. 'wireguard_mesh' on a single zone makes the cluster mesh-capable.
worker_countNoNumber of worker nodes. Default: 1.
credential_idYesUUID of the UpCloud API credential. Get from list_provider_credentials with provider='upcloud'.
control_plane_planNoUpCloud plan for control plane nodes. Default: 'PREMIUM-2xCPU-4GB'.
kubernetes_versionNoVersion for the chosen distribution. With the default distribution (kubeadm) pass a plain upstream tag such as v1.36.4, from list_kubernetes_versions with engine 'kubeadm'. With distribution 'k3s' pass a k3s build such as v1.35.7+k3s1, from engine 'k3s' (a bare patch resolves to its newest +k3sN build). A +k3sN build without distribution 'k3s' is refused. Omit it to install the catalogue's stable version for the distribution.
control_plane_countNoNumber of control plane nodes. Default: 1.
ssh_key_credential_idYesUUID of the SSH key credential. Get from list_provider_credentials with provider='ssh-key'.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / gateway_plan
      Added value: +{
+  "description": "UpCloud NAT gateway plan every node's outbound internet runs through. Default: 'standard' (500 Mbps, two servers). A plan with server_number 1 ('development', 'essentials') cuts all cluster egress while UpCloud rebuilds its one server; two-server plans fail over. Get the plans from list_upcloud_options (gateway_plans).",
+  "type": "string"
+}
  2. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare the mutation profile (readOnlyHint=false, destructiveHint=true, idempotentHint=false), so the bar is lower; the description still adds real value by warning that provisioning starts immediately after creation. It does not mention cost implications or how to observe provisioning progress, but the core behavioral warning is present.

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?

Four tightly packed sentences with zero filler: purpose first, prerequisites second, immediate side effect third, helper tools last. Every sentence earns its place.

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 15-parameter creation tool with no output schema, the description covers what the agent must gather beforehand and the immediate consequence of calling it. It leaves a small gap around post-creation behavior, such as which tool to use to watch provisioning or roll back a failed cluster.

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%, so the schema already documents all 15 parameters, including enums, defaults, and the multi-zone pool constraint. The description only restates the three required credential/zone inputs and the two lookup helpers, adding limited meaning beyond structured data; baseline 3 applies.

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 ('Create and provision a new Kubernetes cluster on UpCloud'), and the provider qualifier cleanly separates it from siblings like create_aws_cluster, create_hetzner_cluster, and create_digitalocean_cluster. No ambiguity about what the tool does.

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?

Gives clear preconditions (API credential, SSH key credential, zone) and routes the agent to the right companion tools: list_provider_credentials for credential IDs and list_instance_types for plan sizes. It stops short of naming alternatives or exclusions, e.g. when to prefer create_managed_cluster or a stack-based path instead.

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

All Ankra toolsInspect
Try in Browser
Context Every Agent Can ShareAgents share what they learn, hand off work, and keep it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources