Skip to main content
Glama

Create Hetzner cluster

create_hetzner_cluster
Destructive

Create and provision a new Kubernetes cluster on Hetzner Cloud. Requires a Hetzner API credential, at least one SSH key credential, and a datacenter location. Optionally configure GitOps by providing a git credential name and repository: GitHub by default, or Bitbucket Cloud with gitops_provider 'bitbucket_cloud'. Optionally provide node_groups to create heterogeneous worker pools instead of a single homogeneous worker pool defined by worker_count and worker_server_type. The cluster will begin provisioning immediately after creation. Use list_provider_credentials to find credential IDs, list_instance_types for server sizes and list prices (it does not show per-location stock: omit the server types to let the platform pick ones the location can provision), and list_gitops_credentials/list_gitops_repositories for GitOps setup.

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>",
      "credential_id": "<credential_id>",
      "location": "<location>"
    },
    "name": "create_hetzner_cluster"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesCluster name. Must be unique within the organisation.
locationYesHetzner datacenter location (e.g., 'fsn1', 'nbg1', 'hel1', 'ash').
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.
node_groupsNoOptional heterogeneous worker pools. When provided, worker_count and worker_server_type are ignored. Each entry creates `count` workers of the given `instance_type` with the given labels and taints.
distributionNoKubernetes distribution. Default: 'kubeadm' (vanilla upstream Kubernetes with Cilium). 'k3s' is the lightweight alternative.
worker_countNoNumber of worker nodes when node_groups is not provided. Must be at least 1 unless node_groups is supplied. Default: 1.
credential_idYesUUID of the Hetzner API credential. Get from list_provider_credentials with provider='hetzner'.
gitops_branchNoGit branch for GitOps. 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.
gitops_repositoryNoGitOps repository: 'owner/repo' on GitHub (e.g., 'org/repo'), 'workspace/repo_slug' on Bitbucket Cloud. Requires gitops_credential_name.
include_networkingNoInclude networking stack (Traefik + cert-manager) configured for hcloud. Default: true, matching the portal create default.
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.
worker_server_typeNoHetzner server type for worker nodes when node_groups is not provided. Omit it and the platform picks the cheapest x86 type the location can provision right now with at least 2 vCPU and 4 GB. The create result names the type it picked.
bastion_server_typeNoHetzner server type for the bastion host. Omit it and the platform picks the cheapest x86 type the location can provision right now with at least 2 vCPU and 4 GB: Hetzner stock varies per location, so there is no fixed default. The create result names the type it picked. An explicit type that the location cannot provision is refused with the available alternatives.
control_plane_countNoNumber of control plane nodes (1 or 3 for HA). Default: 1.
ssh_key_credential_idNoUUID of the primary SSH key credential. Either this or ssh_key_credential_ids must be provided. Get from list_provider_credentials with provider='ssh-key'.
gitops_credential_nameNoName of the git credential for GitOps (from list_gitops_credentials), GitHub or Bitbucket Cloud. Requires gitops_repository, or for Bitbucket Cloud gitops_workspace and gitops_repo_slug.
ssh_key_credential_idsNoOptional list of additional SSH key credential UUIDs to authorise on the cluster servers. Use this to grant multiple users access. Each value must be a UUID returned by list_provider_credentials with provider='ssh-key'.
control_plane_server_typeNoHetzner server type for control plane nodes. Omit it and the platform picks the cheapest x86 type the location can provision right now with at least 4 vCPU and 8 GB. The create result names the type it picked.

Schema Changelog

Changes observed during successful MCP inspections.

  1. 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"
      +}
  2. 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"
      +}
  3. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare readOnlyHint=false, destructiveHint=true, and idempotentHint=false, but the description adds substantial behavior beyond them: provisioning begins immediately after creation, optional parameters have concrete effects, omitted server types are auto-selected by the platform, and certain invalid combinations are refused. It also discloses cross-parameter interactions such as node_groups overriding worker_count and worker_server_type, and gateway_api requiring the networking stack.

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?

The description is front-loaded with the core action and then proceeds through prerequisites, optional configuration, provisioning behavior, and helper tools. It is dense and somewhat long, but the length is justified by the 23-parameter complexity and most sentences carry useful operational information.

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 complex cluster-creation tool with 23 parameters and no output schema, the description covers the necessary prerequisites, key defaults, cross-parameter behavior, refusal conditions, and helper tools for discovering valid values. An agent has enough context to call it correctly without needing additional description text.

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 description coverage is 100%, so the schema already documents each parameter thoroughly and the baseline would be 3. The description still adds meaningful cross-parameter semantics: node_groups replaces homogeneous worker settings, GitOps fields are paired in specific ways, and omitting server types delegates selection to the platform based on per-location stock.

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 states a specific verb and resource: create and provision a new Kubernetes cluster on Hetzner Cloud. It distinguishes itself from sibling create_*_cluster tools by naming the provider and the exact platform context, so an agent can tell what this tool does without opening the schema.

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 prerequisites and operational guidance, including which helper tools to use for credential IDs, instance types, and GitOps setup. It does not explicitly name when not to use this tool versus alternatives such as import_cluster or create_managed_cluster, but the provider-specific context makes the intended use clear.

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.