# KubeStellar MCP (oci · ghcr.io/kubestellar/kubestellar-mcp)

AI-powered Kubernetes diagnostics, RBAC analysis, security checks, and app deployment via MCP

- Trust score: 58/100 (low)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-25

## Components

- oci · `ghcr.io/kubestellar/kubestellar-mcp`: 58/100 (this document), [markdown](https://verifymcp.io/servers/kubestellar-kubestellar-mcp/ghcr-io-kubestellar-kubestellar-mcp.md), [page](https://verifymcp.io/servers/kubestellar-kubestellar-mcp/ghcr-io-kubestellar-kubestellar-mcp)

## Channel facts

- Registry: `oci`
- Package: `ghcr.io/kubestellar/kubestellar-mcp`
- Version: `0.9.20-nightly.20261024`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-25.

- **Supply Chain Security**: 0/100
  - No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
  - Known CVEs could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
  - Install-script risk not yet assessed.
  - Dependency health could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to kubestellar/kubestellar-mcp).
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 0 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 68/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 2376 tokens (~62/item across 38 items; 38 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 90/100
  - Stability observed for 27 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "uninstall_ownership_policy" implies "uninstall" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 38 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the KubeStellar MCP server?

KubeStellar MCP runs locally as a container image, launched with docker run --rm -i -e KUBECONFIG ghcr.io/kubestellar/kubestellar-mcp:0.9.20-nightly.20261024. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add kubestellar-kubestellar-mcp -- docker run --rm -i -e KUBECONFIG ghcr.io/kubestellar/kubestellar-mcp:0.9.20-nightly.20261024
```

This image reads KUBECONFIG. Set it in your client's env block for this server; docker run -e passes it through to the container.

### Cursor

```json
{
  "mcpServers": {
    "kubestellar-kubestellar-mcp": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "KUBECONFIG",
        "ghcr.io/kubestellar/kubestellar-mcp:0.9.20-nightly.20261024"
      ]
    }
  }
}
```

This image reads KUBECONFIG. Set it in your client's env block for this server; docker run -e passes it through to the container.

### VS Code

```json
{
  "servers": {
    "kubestellar-kubestellar-mcp": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "KUBECONFIG",
        "ghcr.io/kubestellar/kubestellar-mcp:0.9.20-nightly.20261024"
      ]
    }
  }
}
```

This image reads KUBECONFIG. Set it in your client's env block for this server; docker run -e passes it through to the container.

### Codex

```bash
codex mcp add kubestellar-kubestellar-mcp -- docker run --rm -i -e KUBECONFIG ghcr.io/kubestellar/kubestellar-mcp:0.9.20-nightly.20261024
```

This image reads KUBECONFIG. Set it in your client's env block for this server; docker run -e passes it through to the container.

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "kubestellar-kubestellar-mcp": {
      "type": "local",
      "command": [
        "docker",
        "run",
        "--rm",
        "-i",
        "-e",
        "KUBECONFIG",
        "ghcr.io/kubestellar/kubestellar-mcp:0.9.20-nightly.20261024"
      ],
      "enabled": true
    }
  }
}
```

This image reads KUBECONFIG. Set it in your client's env block for this server; docker run -e passes it through to the container.

### Hermes

```yaml
mcp_servers:
  kubestellar-kubestellar-mcp:
    command: "docker"
    args: ["run", "--rm", "-i", "-e", "KUBECONFIG", "ghcr.io/kubestellar/kubestellar-mcp:0.9.20-nightly.20261024"]
```

This image reads KUBECONFIG. Set it in your client's env block for this server; docker run -e passes it through to the container.

### Netclaw

```json
{
  "McpServers": {
    "kubestellar-kubestellar-mcp": {
      "Transport": "stdio",
      "Command": "docker",
      "Arguments": [
        "run",
        "--rm",
        "-i",
        "-e",
        "KUBECONFIG",
        "ghcr.io/kubestellar/kubestellar-mcp:0.9.20-nightly.20261024"
      ]
    }
  }
}
```

This image reads KUBECONFIG. Set it in your client's env block for this server; docker run -e passes it through to the container.

### Other

```json
{
  "mcpServers": {
    "kubestellar-kubestellar-mcp": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "KUBECONFIG",
        "ghcr.io/kubestellar/kubestellar-mcp:0.9.20-nightly.20261024"
      ]
    }
  }
}
```

This image reads KUBECONFIG. Set it in your client's env block for this server; docker run -e passes it through to the container.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-24 (score 58, +1)

- [functional] Package version: 0.9.20-nightly.20261023 → 0.9.20-nightly.20261024

### 2026-10-23 (score 57, 0)

- [functional] Package version: 0.9.20-nightly.20261022 → 0.9.20-nightly.20261023

### 2026-10-22 (score 57, +1)

- [security regression] Stability: 0.77 → unverified
- [security regression] Tool safety: pass → unverified
- [functional regression] Capabilities: fail → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] Package version: 0.9.20-nightly.20261021 → 0.9.20-nightly.20261022

### 2026-10-21 (score 56, 0)

- [functional] Package version: 0.9.19-nightly.20261013 → 0.9.20-nightly.20261021
- [functional] Package version: 0.9.20-nightly.20261020 → 0.9.20-nightly.20261021

### 2026-10-20 (score 56, +1)

- [functional] Package version: 0.9.20-nightly.20261019 → 0.9.20-nightly.20261020
- [functional] Package version: 0.9.19-nightly.20261013 → 0.9.20-nightly.20261019

### 2026-10-19 (score 55, 0)

- [security regression] Tool safety: pass → unverified
- [security regression] Stability: 0.67 → unverified
- [functional regression] Capabilities: fail → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] Package version: 0.9.19 → 0.9.20-nightly.20261019
- [functional] Package version: 0.9.19-nightly.20261013 → 0.9.19

### 2026-10-18 (score 55, +1)

- [security regression] Tool safety: pass → unverified
- [security regression] Stability: 0.63 → unverified
- [functional regression] Capabilities: fail → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] Package version: 0.9.19-nightly.20261017 → 0.9.19

### 2026-10-17 (score 54, 0)

- [functional] Package version: 0.9.19-nightly.20261016 → 0.9.19-nightly.20261017

## MCP tools (38)

### `list_clusters` (~45 tokens)

List all discovered Kubernetes clusters from kubeconfig and KubeStellar

Input parameters:

- `source` (string): Discovery source: all, kubeconfig, or kubestellar (not yet implemented)

### `get_cluster_health` (~38 tokens)

Check the health status of a Kubernetes cluster

Input parameters:

- `cluster` (string): Name of the cluster to check (uses current context if not specified)

### `detect_drift` (~111 tokens)

Detect configuration drift between Git repository manifests and cluster state. Shows which resources differ.

Input parameters:

- `branch` (string): Git branch to use (default: main)
- `cluster` (string): Target cluster to check (uses current context if not specified)
- `namespace` (string): Override namespace for all resources
- `path` (string): Path within repository to YAML manifests (e.g., production/)
- `repo_url` (string, required): Git repository URL (e.g., https://github.com/org/manifests)

### `check_gatekeeper` (~39 tokens)

Check if OPA Gatekeeper is installed and running in the cluster

Input parameters:

- `cluster` (string): Cluster name (uses current context if not specified)

### `get_ownership_policy_status` (~39 tokens)

Get the status of the ownership labels policy including violation count

Input parameters:

- `cluster` (string): Cluster name (uses current context if not specified)

### `list_ownership_violations` (~70 tokens)

List resources that violate the ownership labels policy (missing owner/team labels)

Input parameters:

- `cluster` (string): Cluster name (uses current context if not specified)
- `limit` (integer): Maximum number of violations to return (default 50)
- `namespace` (string): Filter violations by namespace

### `install_ownership_policy` (~128 tokens)

Install the ownership labels policy (ConstraintTemplate and Constraint) for OPA Gatekeeper

Input parameters:

- `cluster` (string): Cluster name (uses current context if not specified)
- `exclude_namespaces` (array): Namespaces to exclude (default: kube-*, openshift-*, gatekeeper-system)
- `labels` (array): Required labels (default: ["owner", "team"])
- `mode` (string): Enforcement mode: dryrun, warn, or enforce (default: dryrun)
- `target_namespaces` (array): Namespaces to enforce (empty means all non-system namespaces)

### `set_ownership_policy_mode` (~54 tokens)

Change the enforcement mode of the ownership labels policy

Input parameters:

- `cluster` (string): Cluster name (uses current context if not specified)
- `mode` (string, required): Enforcement mode: dryrun, warn, or enforce

### `uninstall_ownership_policy` (~35 tokens)

Remove the ownership labels policy from the cluster

Input parameters:

- `cluster` (string): Cluster name (uses current context if not specified)

### `get_roles` (~48 tokens)

List Roles in a namespace

Input parameters:

- `cluster` (string): Cluster name (uses current context if not specified)
- `namespace` (string): Namespace to list roles from (all namespaces if not specified)

### `get_cluster_roles` (~51 tokens)

List ClusterRoles in a cluster

Input parameters:

- `cluster` (string): Cluster name (uses current context if not specified)
- `include_system` (string): Include system ClusterRoles (true/false, default false)

### `get_role_bindings` (~52 tokens)

List RoleBindings in a namespace

Input parameters:

- `cluster` (string): Cluster name (uses current context if not specified)
- `namespace` (string): Namespace to list role bindings from (all namespaces if not specified)

### `get_cluster_role_bindings` (~55 tokens)

List ClusterRoleBindings in a cluster

Input parameters:

- `cluster` (string): Cluster name (uses current context if not specified)
- `include_system` (string): Include system ClusterRoleBindings (true/false, default false)

### `can_i` (~132 tokens)

Check if a subject can perform an action on a resource (similar to kubectl auth can-i)

Input parameters:

- `cluster` (string): Cluster name (uses current context if not specified)
- `name` (string): Specific resource name to check
- `namespace` (string): Namespace for the check (empty for cluster-scoped)
- `resource` (string, required): The resource type (pods, deployments, secrets, etc.)
- `subresource` (string): Subresource (e.g., logs, status)
- `verb` (string, required): The action verb (get, list, create, update, delete, watch, etc.)

### `analyze_subject_permissions` (~86 tokens)

Analyze all RBAC permissions for a specific subject (user, group, or service account)

Input parameters:

- `cluster` (string): Cluster name (uses current context if not specified)
- `namespace` (string): Namespace for ServiceAccount subjects
- `subject_kind` (string, required): Kind of subject: User, Group, or ServiceAccount
- `subject_name` (string, required): Name of the subject

### `describe_role` (~66 tokens)

Get detailed information about a Role or ClusterRole including all rules

Input parameters:

- `cluster` (string): Cluster name (uses current context if not specified)
- `name` (string, required): Name of the Role or ClusterRole
- `namespace` (string): Namespace for Role (omit for ClusterRole)

### `audit_kubeconfig` (~48 tokens)

Audit all clusters in kubeconfig: check connectivity, identify stale/inaccessible clusters, and recommend cleanup

Input parameters:

- `timeout_seconds` (integer): Connection timeout in seconds per cluster (default 5)

### `find_resource_owners` (~79 tokens)

Find who owns/manages resources by checking managedFields, ownership labels, and annotations

Input parameters:

- `cluster` (string): Cluster name (uses current context if not specified)
- `namespace` (string, required): Namespace to check (required)
- `resource_type` (string): Resource type to check: pods, deployments, services, all (default: all)

### `get_pods` (~70 tokens)

List pods in a cluster

Input parameters:

- `cluster` (string): Cluster name (uses current context if not specified)
- `label_selector` (string): Label selector to filter pods (e.g., app=nginx)
- `namespace` (string): Namespace to list pods from (all namespaces if not specified)

### `get_deployments` (~50 tokens)

List deployments in a cluster

Input parameters:

- `cluster` (string): Cluster name (uses current context if not specified)
- `namespace` (string): Namespace to list deployments from (all namespaces if not specified)

### `get_services` (~48 tokens)

List services in a cluster

Input parameters:

- `cluster` (string): Cluster name (uses current context if not specified)
- `namespace` (string): Namespace to list services from (all namespaces if not specified)

### `get_nodes` (~30 tokens)

List nodes in a cluster

Input parameters:

- `cluster` (string): Cluster name (uses current context if not specified)

### `get_events` (~70 tokens)

Get recent events from a cluster, useful for troubleshooting

Input parameters:

- `cluster` (string): Cluster name (uses current context if not specified)
- `limit` (integer): Maximum number of events to return (default 50)
- `namespace` (string): Namespace to get events from (all namespaces if not specified)

### `describe_pod` (~55 tokens)

Get detailed information about a specific pod

Input parameters:

- `cluster` (string): Cluster name (uses current context if not specified)
- `name` (string, required): Name of the pod
- `namespace` (string): Namespace of the pod

### `get_pod_logs` (~90 tokens)

Get logs from a pod

Input parameters:

- `cluster` (string): Cluster name (uses current context if not specified)
- `container` (string): Container name (required if pod has multiple containers)
- `name` (string, required): Name of the pod
- `namespace` (string): Namespace of the pod
- `tail_lines` (integer): Number of lines from the end to return (default 100)

### `find_pod_issues` (~88 tokens)

Find pods with issues like CrashLoopBackOff, ImagePullBackOff, Pending, OOMKilled, or restarts

Input parameters:

- `cluster` (string): Cluster name (uses current context if not specified)
- `include_completed` (string): Include completed/succeeded pods (true/false, default false)
- `namespace` (string): Namespace to check (all namespaces if not specified)

### `find_deployment_issues` (~60 tokens)

Find deployments with issues like unavailable replicas, stuck rollouts, or misconfigurations

Input parameters:

- `cluster` (string): Cluster name (uses current context if not specified)
- `namespace` (string): Namespace to check (all namespaces if not specified)

### `check_resource_limits` (~54 tokens)

Find pods/containers without CPU or memory limits/requests configured

Input parameters:

- `cluster` (string): Cluster name (uses current context if not specified)
- `namespace` (string): Namespace to check (all namespaces if not specified)

### `check_security_issues` (~64 tokens)

Find security misconfigurations: privileged containers, running as root, host network/PID, missing security context

Input parameters:

- `cluster` (string): Cluster name (uses current context if not specified)
- `namespace` (string): Namespace to check (all namespaces if not specified)

### `analyze_namespace` (~50 tokens)

Comprehensive namespace analysis: resource quotas, limit ranges, pod count, issues summary

Input parameters:

- `cluster` (string): Cluster name (uses current context if not specified)
- `namespace` (string, required): Namespace to analyze

### `get_warning_events` (~80 tokens)

Get only Warning events, filtered by namespace or resource

Input parameters:

- `cluster` (string): Cluster name (uses current context if not specified)
- `involved_object` (string): Filter by involved object name
- `limit` (integer): Maximum number of events (default 50)
- `namespace` (string): Namespace to check (all namespaces if not specified)

### `detect_cluster_type` (~54 tokens)

Detect the Kubernetes distribution type (OpenShift, EKS, GKE, AKS, kubeadm, k3s, kind, etc.)

Input parameters:

- `cluster` (string): Cluster name (uses current context if not specified)

### `get_cluster_version_info` (~38 tokens)

Get current Kubernetes/OpenShift version and check for available upgrades

Input parameters:

- `cluster` (string): Cluster name (uses current context if not specified)

### `check_olm_operator_upgrades` (~58 tokens)

Check OLM-managed operators for available upgrades (requires OLM installed)

Input parameters:

- `cluster` (string): Cluster name (uses current context if not specified)
- `namespace` (string): Namespace to check (all namespaces if not specified)

### `check_helm_release_upgrades` (~53 tokens)

Check Helm releases for available chart version upgrades

Input parameters:

- `cluster` (string): Cluster name (uses current context if not specified)
- `namespace` (string): Namespace to check (all namespaces if not specified)

### `get_upgrade_prerequisites` (~47 tokens)

Check upgrade prerequisites: node health, pod issues, ClusterOperators (OpenShift), MachineConfigPools

Input parameters:

- `cluster` (string): Cluster name (uses current context if not specified)

### `trigger_openshift_upgrade` (~98 tokens)

Trigger an OpenShift cluster upgrade to a specific version (REQUIRES CONFIRMATION: pass confirm='yes-upgrade-now')

Input parameters:

- `cluster` (string): Cluster name (uses current context if not specified)
- `confirm` (string, required): Must be 'yes-upgrade-now' to proceed with the upgrade
- `target_version` (string, required): Target OpenShift version to upgrade to (e.g., 4.14.5)

### `get_upgrade_status` (~43 tokens)

Get the current upgrade status for a cluster (progress, ClusterOperators, MachineConfigPools)

Input parameters:

- `cluster` (string): Cluster name (uses current context if not specified)

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/kubestellar-kubestellar-mcp/ghcr-io-kubestellar-kubestellar-mcp#diagnostics

## Score history

- 2026-10-25: 58
- 2026-10-24: 58
- 2026-10-23: 57
- 2026-10-22: 57
- 2026-10-21: 56
- 2026-10-20: 56
- 2026-10-19: 55
- 2026-10-18: 55
- 2026-10-17: 54
- 2026-10-16: 54
- 2026-10-15: 54
- 2026-10-14: 53
- 2026-10-13: 20
- 2026-10-12: 20
- 2026-10-11: 19
- 2026-10-07: 20
- 2026-10-05: 49
- 2026-10-04: 48
- 2026-10-03: 48
- 2026-10-02: 47
- 2026-10-01: 47
- 2026-09-30: 46
- 2026-09-29: 46
- 2026-09-28: 46

## Common questions

### What is the KubeStellar MCP server?

KubeStellar MCP is listed in the public MCP registry as io.github.kubestellar/kubestellar-mcp. AI-powered Kubernetes diagnostics, RBAC analysis, security checks, and app deployment via MCP. This page covers its container image (ghcr.io/kubestellar/kubestellar-mcp).

### Is the KubeStellar MCP server safe to use?

KubeStellar MCP scores 58 out of 100 on VerifyMCP. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the KubeStellar MCP server expose?

KubeStellar MCP exposes 38 tools: list_clusters, get_cluster_health, detect_drift, check_gatekeeper, get_ownership_policy_status, and 33 more. Their descriptions and schemas cost roughly 2,376 tokens of context every time the server is loaded.

### Is the KubeStellar MCP server still maintained?

KubeStellar MCP is still listed as active in the MCP registry. We last reached this channel on 25 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the KubeStellar MCP server under?

KubeStellar MCP declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- GitHub Container Registry: https://ghcr.io/kubestellar/kubestellar-mcp
- Repository: https://github.com/kubestellar/kubestellar-mcp
- Changelog RSS feed: https://verifymcp.io/servers/kubestellar-kubestellar-mcp/ghcr-io-kubestellar-kubestellar-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/kubestellar-kubestellar-mcp/ghcr-io-kubestellar-kubestellar-mcp.json
- HTML version of this page: https://verifymcp.io/servers/kubestellar-kubestellar-mcp/ghcr-io-kubestellar-kubestellar-mcp