Skip to main content
Glama

Create Ankra Cloud cluster

create_ankracloud_cluster
Destructive

Create and provision a new self-managed Kubernetes cluster on Ankra Cloud: k3s or kubeadm on Ankra Cloud servers in one zone, reached through a bastion server. By default the cluster is IPv6-only (network_mode ipv6_only): the bastion holds only its public IPv6, which the platform reaches through an Ankra Cloud port forward, and the nodes reach IPv4 through the zone's NAT64 (the zone must offer NAT64 and port forwarding; the preflight refuses otherwise). Only when the user asks for public IPv4, network_mode ipv4_nat adds a router with NAT for the nodes' egress and gives the bastion a public IPv4 (a paid add-on under the account's public IPv4 quota). Ankra creates a private network (or adopts private_network_id) and a firewall that admits only the private network to the nodes; the Ankra Cloud cloud controller manager is always installed. The organisation's built-in Ankra Cloud credential is used unless credential_id names a stored one (list_provider_credentials with provider='ankracloud'). Zones and plans come from list_managed_k8s_options with provider='ankracloud_k8s': its locations are the zones and its node sizes are the plans, with monthly prices. The create runs a preflight first (credential, billing standing of the built-in account, zone offers compute, every plan and the template exist, an adopted network lives in the zone, quota) and refuses with every failing item when it cannot proceed; nothing is written on refusal. A managed Ankra Cloud Kubernetes cluster (Ankra Cloud runs the control plane) is create_managed_cluster with provider='ankracloud_k8s', not this tool. Only available to organisations with Ankra Cloud enabled.

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": {
      "name": "<name>",
      "zone": "<zone>",
      "bastion_plan": "<bastion_plan>",
      "control_plane_plan": "<control_plane_plan>"
    },
    "name": "create_ankracloud_cluster"
  }
}

Input Schema

NameRequiredDescriptionDefault
cniNoContainer network plugin. Default: 'cilium'. kubeadm accepts only cilium.
nameYesCluster name. Must be unique within the organisation.
zoneYesAnkra Cloud zone the servers are placed in (e.g., 'se-sto1'). Get the deployable zones from list_managed_k8s_options with provider='ankracloud_k8s'.
templateNoPublic Ankra Cloud operating-system template every server boots. Default: 'debian-13'.
descriptionNoOptional cluster description.
environmentNoWhat the cluster is for. Ankra's autonomy gates treat a cluster like production until a person confirms what it is for. A label named here is that confirmation only when a member confirms this call's card in Ankra chat; over MCP, or with no member's confirmation, it is recorded as set by automation and confirms nothing (a production label is still honoured). Omit it and the cluster is labelled development, recorded as a default nobody confirmed.
gateway_apiNoAlso serve the Kubernetes Gateway API: the cluster's Traefik serves Gateway API routes (HTTPRoute) next to Ingress, and Ingress keeps working. Adds the Gateway API CRDs, a shared traefik-gateway Gateway in the traefik namespace (a plain HTTP listener that accepts routes from every namespace), and cert-manager and external-dns support for those routes. Needs the networking stack (on by default): asking for it with include_networking=false is refused. Default: false. Set at create only; no tool turns it on or off on an existing cluster.
include_dnsNoProvision the cluster's Ankra-managed DNS zone. Default: true.
worker_planNoAnkra Cloud plan for worker nodes. Required when worker_count is above zero.
bastion_planYesAnkra Cloud plan for the bastion server (e.g., 'premium-2xcpu-4gb'). Plans are the node sizes list_managed_k8s_options returns for provider='ankracloud_k8s'.
distributionNoKubernetes distribution. Default: 'kubeadm' (vanilla upstream Kubernetes with Cilium). 'k3s' is the lightweight alternative. kubeadm supports only the cilium CNI on Ankra Cloud.
network_modeNoipv6_only (default): no public IPv4 anywhere. ipv4_nat: a NAT router and a bastion with a public IPv4; use it only when the user asks for public IPv4.
worker_countNoNumber of worker nodes. Default: 1.
credential_idNoUUID of the Ankra Cloud credential. Get from list_provider_credentials with provider='ankracloud'. Omit it to use the organisation's built-in Ankra Cloud credential, which is the normal case.
gitops_branchNoBranch of the GitOps repository. Default: 'master'.
gitops_providerNoProvider of the GitOps repository: 'github' (the default when omitted) or 'bitbucket_cloud'. Pass the credential's provider from list_gitops_credentials.
gitops_repo_slugNoBitbucket Cloud repository slug of the GitOps repository (from list_gitops_repositories). Only with gitops_provider 'bitbucket_cloud', together with gitops_workspace.
gitops_workspaceNoBitbucket Cloud workspace of the GitOps repository (from list_gitops_repositories). Only with gitops_provider 'bitbucket_cloud', together with gitops_repo_slug.
network_ip_rangeNoCreated network only: the private IPv4 CIDR Ankra creates the cluster network with. Omit it for a range derived per cluster. Refused alongside private_network_id.
retention_policyNoStorage retention on teardown. Default: 'retain'.
worker_disk_tierNoStorage tier of each worker's root disk. Omit it for the zone's default tier. local-nvme puts the disk on the node's own fast disks (the right choice for CI nodes); standard, maxiops and hdd are the zone's Ankra Storage tiers.
bastion_disk_tierNoStorage tier of the bastion's root disk. Omit it for the zone's default tier. local-nvme puts the disk on the node's own fast disks (the right choice for CI nodes); standard, maxiops and hdd are the zone's Ankra Storage tiers.
gitops_repositoryNoOptional GitOps repository to connect at creation: 'owner/repo' on GitHub, 'workspace/repo_slug' on Bitbucket Cloud; requires gitops_credential_name.
sandbox_node_planNoServer plan of the sandbox nodes. Defaults to worker_plan.
control_plane_planYesAnkra Cloud plan for control plane nodes.
include_networkingNoInstall the platform networking stack (ingress, cert-manager, external-dns). Default: true.
kubernetes_versionNoKubernetes version. If not specified, uses the latest supported version.
private_network_idNoId of an existing Ankra Cloud private network in the same zone to adopt; it is never deleted with the cluster. Refused alongside network_ip_range. Omit it to have Ankra create a private network for the cluster.
sandbox_node_countNoNodes in a separate node group running the gVisor sandbox runtime, beside the workers. Ankra AI runs code on its own (fixing a build, regenerating a lockfile) only behind a sandbox, so set this on a cluster that will run CI or Ankra AI's workspaces: 1 is enough to start. kubeadm clusters only. Leave it out for a cluster that runs only applications.
bastion_allowed_ipsNoIPv4 or IPv6 addresses or CIDRs allowed to SSH to the bastion's public address (its IPv6, or its IPv4 with network_mode ipv4_nat; e.g., '2001:db8::/32'). Omit it to admit SSH from the internet; access is still key-only.
control_plane_countNoNumber of control plane nodes. Default: 1.
ssh_key_credential_idNoUUID of an SSH key credential to install on the bastion and nodes. Get from list_provider_credentials with provider='ssh-key'. Omit it to use only the key Ankra generates for the cluster.
worker_disk_gibibytesNoRoot disk size of each worker in GiB. Omit it for the plan's included disk. Keep it small when workloads keep their data on persistent volumes.
bastion_disk_gibibytesNoRoot disk size of the bastion in GiB. Omit it for the plan's included disk. Ankra Cloud refuses a size below the plan's and the template's minimum.
gitops_credential_nameNoName of the git credential, GitHub or Bitbucket Cloud, that can read the GitOps repository (see list_gitops_credentials). Requires gitops_repository, or for Bitbucket Cloud gitops_workspace and gitops_repo_slug.
control_plane_disk_tierNoStorage tier of each control plane's root disk. Omit it for the zone's default tier. local-nvme puts the disk on the node's own fast disks (the right choice for CI nodes); standard, maxiops and hdd are the zone's Ankra Storage tiers.
control_plane_disk_gibibytesNoRoot disk size of each control plane in GiB. Omit it for the plan's included disk.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / sandbox_node_count
      Added value: +{
      +  "description": "Nodes in a separate node group running the gVisor sandbox runtime, beside the workers. Ankra AI runs code on its own (fixing a build, regenerating a lockfile) only behind a sandbox, so set this on a cluster that will run CI or Ankra AI's workspaces: 1 is enough to start. kubeadm clusters only. Leave it out for a cluster that runs only applications.",
      +  "minimum": 0,
      +  "type": "integer"
      +}
    • addedInput schema / properties / sandbox_node_plan
      Added value: +{
      +  "description": "Server plan of the sandbox nodes. Defaults to worker_plan.",
      +  "type": "string"
      +}
  2. Changed1 schema field changed
    • addedInput schema / properties / environment
      Added value: +{
      +  "description": "What the cluster is for. Ankra's autonomy gates treat a cluster like production until a person confirms what it is for. A label named here is that confirmation only when a member confirms this call's card in Ankra chat; over MCP, or with no member's confirmation, it is recorded as set by automation and confirms nothing (a production label is still honoured). Omit it and the cluster is labelled development, recorded as a default nobody confirmed.",
      +  "enum": [
      +    "development",
      +    "staging",
      +    "testing",
      +    "production",
      +    "local"
      +  ],
      +  "type": "string"
      +}
  3. Changed1 schema field changed
    • addedInput schema / properties / gateway_api
      Added value: +{
      +  "description": "Also serve the Kubernetes Gateway API: the cluster's Traefik serves Gateway API routes (HTTPRoute) next to Ingress, and Ingress keeps working. Adds the Gateway API CRDs, a shared traefik-gateway Gateway in the traefik namespace (a plain HTTP listener that accepts routes from every namespace), and cert-manager and external-dns support for those routes. Needs the networking stack (on by default): asking for it with include_networking=false is refused. Default: false. Set at create only; no tool turns it on or off on an existing cluster.",
      +  "type": "boolean"
      +}
  4. Changed2 schema fields changed
    • changedInput schema / properties / bastion_allowed_ips / description
      Previous value: -"IPv4 or IPv6 addresses or CIDRs allowed to SSH to the bastion's public IPv4 (e.g., '203.0.113.4/32'). Omit it to admit SSH from the internet; access is still key-only."New value: +"IPv4 or IPv6 addresses or CIDRs allowed to SSH to the bastion's public address (its IPv6, or its IPv4 with network_mode ipv4_nat; e.g., '2001:db8::/32'). Omit it to admit SSH from the internet; access is still key-only."
    • addedInput schema / properties / network_mode
      Added value: +{
      +  "description": "ipv6_only (default): no public IPv4 anywhere. ipv4_nat: a NAT router and a bastion with a public IPv4; use it only when the user asks for public IPv4.",
      +  "enum": [
      +    "ipv6_only",
      +    "ipv4_nat"
      +  ],
      +  "type": "string"
      +}
  5. Changed6 schema fields changed
    • addedInput schema / properties / bastion_disk_gibibytes
      Added value: +{
      +  "description": "Root disk size of the bastion in GiB. Omit it for the plan's included disk. Ankra Cloud refuses a size below the plan's and the template's minimum.",
      +  "maximum": 4096,
      +  "minimum": 1,
      +  "type": "integer"
      +}
    • addedInput schema / properties / bastion_disk_tier
      Added value: +{
      +  "description": "Storage tier of the bastion's root disk. Omit it for the zone's default tier. local-nvme puts the disk on the node's own fast disks (the right choice for CI nodes); standard, maxiops and hdd are the zone's Ankra Storage tiers.",
      +  "enum": [
      +    "local-nvme",
      +    "standard",
      +    "maxiops",
      +    "hdd"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / control_plane_disk_gibibytes
      Added value: +{
      +  "description": "Root disk size of each control plane in GiB. Omit it for the plan's included disk.",
      +  "maximum": 4096,
      +  "minimum": 1,
      +  "type": "integer"
      +}
    • addedInput schema / properties / control_plane_disk_tier
      Added value: +{
      +  "description": "Storage tier of each control plane's root disk. Omit it for the zone's default tier. local-nvme puts the disk on the node's own fast disks (the right choice for CI nodes); standard, maxiops and hdd are the zone's Ankra Storage tiers.",
      +  "enum": [
      +    "local-nvme",
      +    "standard",
      +    "maxiops",
      +    "hdd"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / worker_disk_gibibytes
      Added value: +{
      +  "description": "Root disk size of each worker in GiB. Omit it for the plan's included disk. Keep it small when workloads keep their data on persistent volumes.",
      +  "maximum": 4096,
      +  "minimum": 1,
      +  "type": "integer"
      +}
    • addedInput schema / properties / worker_disk_tier
      Added value: +{
      +  "description": "Storage tier of each worker's root disk. Omit it for the zone's default tier. local-nvme puts the disk on the node's own fast disks (the right choice for CI nodes); standard, maxiops and hdd are the zone's Ankra Storage tiers.",
      +  "enum": [
      +    "local-nvme",
      +    "standard",
      +    "maxiops",
      +    "hdd"
      +  ],
      +  "type": "string"
      +}
  6. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only say non-readonly, non-idempotent, destructive; the description adds far more: a preflight that checks credential, billing standing, zone compute, plan/template existence, adopted-network zone and quota, and 'refuses with every failing item ... nothing is written on refusal'. It also discloses the network/firewall side effects it creates, that an adopted private_network_id is 'never deleted with the cluster', and that the cloud controller manager is always installed.

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?

Purpose is front-loaded in the opening clause, and each following sentence carries distinct information (network mode, preflight, alternative tool, org gating) appropriate to a 37-parameter tool. It is a single dense paragraph with heavy parenthetical nesting, and some material (IPv6-only behavior, CNI constraints) is restated from the schema descriptions, which costs it a point.

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 high-complexity, non-idempotent, destructive provisioning call with no output schema, the description covers prerequisites, validation order, failure semantics, cost/quota implications, credential resolution, network adoption, and the sibling tool to use instead. Nothing an agent must know to call this safely is missing.

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, but the description adds cross-tool sourcing rules the schema lacks: zones and plans 'come from list_managed_k8s_options with provider='ankracloud_k8s'', and the built-in credential is used unless credential_id is set. It also explains conflicts (network_ip_range refused alongside private_network_id) and the default-vs-add-on quota implication of network_mode. It does not cover the GitOps parameter interactions as thickly, so not a 5.

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 first sentence gives a specific verb and resource with scope qualifiers: 'Create and provision a new self-managed Kubernetes cluster on Ankra Cloud: k3s or kubeadm', plus the bastion topology. It explicitly disambiguates against the closest sibling by name: 'A managed Ankra Cloud Kubernetes cluster ... is create_managed_cluster with provider='ankracloud_k8s', not this tool.' That contrast with the other create_*_cluster tools is exactly what an agent needs to choose correctly.

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?

It states when to pick each mode: ipv6_only is default, ipv4_nat 'Only when the user asks for public IPv4', and names the paid add-on and quota it consumes. It also gives conditional guidance inside the run ('Only available to organisations with Ankra Cloud enabled', sandbox_node_count when the cluster runs CI), names the alternative tool for managed clusters, and says nothing is written on preflight refusal.

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.