An MCP server that gives AI assistants full control over Helm - from chart discovery to deployments.
712
Give your AI assistant safe, structured access to Helm v3 and Kubernetes. Search charts, validate values, preview diffs, install or upgrade releases, and roll back broken deployments—with secrets redacted automatically.
latest, 0.5.1linux/amd64, linux/arm64talkops-helm-mcp-serverhelm:// for structured context discovery/app/skills (browse on GitHub)helm v3 and kubectl inside a minimal non-root image (linux/amd64, linux/arm64).MCP_ALLOW_WRITE=true.stdio)Use this configuration in Claude Desktop, Cursor, Windsurf, or VS Code (mcp.json / claude_desktop_config.json):
{
"mcpServers": {
"helm": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"MCP_TRANSPORT=stdio",
"-v",
"/path/to/your/kubeconfig:/app/.kube/config:ro",
"talkopsai/helm-mcp-server:latest"
]
}
}
}
Using Claude Code? Register it in one command:
claude mcp add helm -- docker run -i --rm -e MCP_TRANSPORT=stdio -v ~/.kube/config:/app/.kube/config:ro talkopsai/helm-mcp-server:latest
Tip: If your kubeconfig references external client certificate files (for example with
minikubeorkind), mount the full~/.kubedirectory (-v /path/to/.kube:/app/.kube:ro) so those files are reachable inside the container.
Restart your MCP client and try asking:
database namespace."my-app to chart version 2.1.0."redis release is failing. What's wrong and how do I roll it back?"By default (MCP_TRANSPORT=http), the container starts an MCP Streamable HTTP server on port 8765 so multiple clients can share a single instance:
docker run --rm -p 8765:8765 \
-v ~/.kube/config:/app/.kube/config:ro \
talkopsai/helm-mcp-server:latest
Point your MCP client at http://localhost:8765/mcp:
{
"mcpServers": {
"helm": {
"url": "http://localhost:8765/mcp"
}
}
}
Out of the box, the container runs in read-only mode (MCP_ALLOW_WRITE=false). To allow mutations (installing, upgrading, rolling back, or uninstalling releases and adding chart repositories), pass -e MCP_ALLOW_WRITE=true to docker run. Even with writes enabled, changes support dry-run previews and destructive operations require explicit confirmation.
| Variable | Container Default | Description |
|---|---|---|
KUBECONFIG | /app/.kube/config | Path to mounted kubeconfig inside the container |
MCP_ALLOW_WRITE | false | Set to true to enable install, upgrade, rollback, and uninstall tools |
MCP_TOOLSETS | all | Filter tools: read, mutate, or all |
HELM_TIMEOUT | 300 | Timeout in seconds for Helm CLI operations |
MCP_TRANSPORT | http | http (standalone server) or stdio (MCP client subprocess) |
MCP_PORT | 8765 | HTTP listen port inside the container |
| Tool | Access | Description |
|---|---|---|
helm_ensure_repository | Write | Add and index a Helm chart repository if not already configured. |
helm_get_release_status | Read | Get concise current status, revision, resource counts, and resource URIs for a Helm release. |
helm_install_chart | Write (destructive) | Install a new Helm release onto the active Kubernetes cluster context. |
helm_list_releases | Read | List Helm releases in the active cluster with optional namespace/status filtering and pagination. |
helm_monitor_deployment | Read | Evaluate Helm release status, Deployment/StatefulSet rollouts, and container failure states. |
helm_plan_release | Read | Compute a pre-deployment plan for a Helm release (install preview if new; resource/image/replica diff if existing). |
helm_render_manifests | Read | Render Kubernetes manifests from a Helm chart offline with automatic Secret data redaction. |
helm_rollback_release | Write (destructive) | Roll back a Helm release to a previous revision (or simulate with dry_run=True). |
helm_search_charts | Read | Search configured Helm chart repositories by keyword. |
helm_uninstall_release | Write (destructive) | Uninstall a Helm release and delete its managed Kubernetes resources. |
helm_upgrade_release | Write (destructive) | Upgrade an existing Helm release to a new chart version or values configuration. |
kubernetes_check_prerequisites | Read | Verify whether the active cluster meets minimum Kubernetes version and API resource/CRD requirements. |
kubernetes_set_context | Write | Switch the active Kubernetes cluster context for all subsequent Helm and Kubernetes calls in this session. |
This image also ships step-by-step operational playbooks (SKILL.md) under /app/skills:
deploying-helm-chartsreviewing-helm-release-securitytroubleshooting-helm-releasesupgrading-and-rolling-back-helm-releasesTo copy the skills onto your workstation for Claude Code or Cursor:
docker run --rm --entrypoint tar talkopsai/helm-mcp-server:latest -C /app/skills -cf - . | tar -xf - -C ~/.claude/skills/
Content type
Image
Digest
sha256:07690b576…
Size
118 MB
Last updated
3 days ago
docker pull talkopsai/helm-mcp-server