Rancher MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RANCHER_TIMEOUT | No | HTTP timeout in seconds. | 60 |
| RANCHER_BASE_URL | No | Rancher Manager base URL (no trailing slash). | https://localhost |
| RANCHER_API_TOKEN | Yes | API token in `token-xxx:yyy...` format. | |
| RANCHER_VERIFY_SSL | No | Verify TLS certificates. | true |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_clustersA | List all clusters managed by this Rancher server. |
| get_clusterA | Get detailed information about a specific Rancher cluster. Args:
cluster_id: Rancher-assigned cluster identifier (e.g. |
| list_projectsA | List Rancher projects, optionally filtered by cluster. Args: cluster_id: Optional cluster ID used to scope the result. |
| list_nodesB | List nodes belonging to a Rancher-managed cluster. Args: cluster_id: Rancher-assigned cluster identifier. |
| list_namespacesB | List namespaces in the Kubernetes cluster via the Rancher proxy. Args: cluster_id: Rancher-assigned cluster identifier. |
| list_podsA | List pods in a cluster, optionally scoped to a namespace. Args: cluster_id: Rancher-assigned cluster identifier. namespace: Optional namespace to filter pods. |
| list_deploymentsB | List Deployments in a cluster, optionally scoped to a namespace. Args: cluster_id: Rancher-assigned cluster identifier. namespace: Optional namespace to filter deployments. |
| get_pod_logsA | Fetch logs from a pod via the Rancher Kubernetes proxy. Args: cluster_id: Rancher-assigned cluster identifier. namespace: Namespace the pod lives in. pod_name: Name of the pod whose logs should be returned. tail_lines: Number of trailing lines to return (default 100). |
| scale_deploymentB | Scale a Kubernetes Deployment to the given replica count. Args: cluster_id: Rancher-assigned cluster identifier. namespace: Namespace containing the deployment. name: Deployment name. replicas: Desired replica count. |
| list_catalog_appsB | List catalog applications installed in a Rancher cluster. Args: cluster_id: Rancher-assigned cluster identifier. |
| create_kubeconfigA | Generate a kubeconfig document for the given cluster. Args: cluster_id: Rancher-assigned cluster identifier. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 11 tools
Each tool targets a distinct resource or action (clusters, kubeconfig, pods, deployments, namespaces, nodes, projects, catalog apps). There is no overlap; even related tools like 'list_clusters' and 'get_cluster' are clearly different operations.
All tools follow a consistent verb_noun pattern (create_, get_, list_, scale_). The naming style is uniform and predictable, making it easy for an agent to infer the function of each tool.
With 11 tools, the server is well-scoped for a Rancher management interface. It covers a variety of essential operations without being bloated or too sparse.
The tool set is heavily read-oriented (list, get) with only two write operations (create_kubeconfig, scale_deployment). Missing critical CRUD operations for clusters, deployments, and other resources, which limits agent capabilities for full lifecycle management.