Radar
The missing open source Kubernetes UI. Topology, event timeline, and service traffic — plus resource browsing and Helm management.
What is Radar?
Radar is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to missing open source kubernetes ui. topology, event timeline, and service traffic — plus resource browsing and helm management.
The missing open source Kubernetes UI. Topology, event timeline, and service traffic — plus resource browsing and Helm management.
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- The missing open source Kubernetes UI. Topology, event timel
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx radarConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Radar
Radar is an open-source Kubernetes UI and MCP server that provides cluster topology visualization, event timelines, service traffic graphs, resource browsing, and Helm and GitOps management through a single interface. Its built-in MCP server exposes AI-ready tools for cluster security auditing, GitOps workflow control (FluxCD/ArgoCD), and RBAC permission inspection, letting AI assistants like Claude diagnose cluster issues, check security posture, and trigger reconciliation without kubectl expertise. Platform engineers and SREs use Radar as both an interactive browser-based UI and as a structured Kubernetes intelligence layer for AI agents.
Prerequisites
- A running Kubernetes cluster (GKE, EKS, AKS, minikube, kind, k3s, or any conformant cluster)
- kubectl configured with a valid kubeconfig (~/.kube/config) and API access to the cluster
- For Helm install: Helm 3+ installed
- An MCP client such as Claude Desktop, Cursor, or GitHub Copilot
- Optional: Prometheus or VictoriaMetrics for cost and metrics insights
Install Radar
Choose the installation method that fits your environment. The quick installer script works on Linux and macOS. Homebrew and Krew are also supported.
# Quick install (Linux/macOS)
curl -fsSL https://get.radarhq.io | sh
# Homebrew (macOS/Linux)
brew install skyhook-io/tap/radar
# kubectl plugin via Krew
kubectl krew install radar
# Windows via Scoop
scoop bucket add skyhook https://github.com/skyhook-io/scoop-bucket
scoop install radarStart the Radar server
Run Radar against your cluster. By default it reads ~/.kube/config and starts a web server on port 9280. Key flags let you set the namespace, storage backend, and authentication mode.
kubectl radar
# With options
radar --port 9280 --namespace production --timeline-storage sqliteDeploy in-cluster with Helm (optional)
For persistent in-cluster deployment, use the official Helm chart. This installs Radar as a pod in its own namespace.
helm repo add skyhook https://skyhook-io.github.io/helm-charts
helm install radar skyhook/radar -n radar --create-namespaceConfigure your MCP client
Radar's MCP server runs automatically alongside the web UI. Point your MCP client at the Radar HTTP endpoint. The MCP server can be disabled with --no-mcp if you only want the UI.
{
"mcpServers": {
"radar": {
"type": "http",
"url": "http://localhost:9280/mcp"
}
}
}Use AI tools against your cluster
With the MCP connection established, your AI client can call get_cluster_audit for security and reliability scanning (31 checks), manage_gitops to sync/suspend/resume ArgoCD or FluxCD applications, and get_subject_permissions to inspect RBAC for any ServiceAccount or user.
Radar Examples
Client configuration
Claude Desktop configuration for Radar running locally. If Radar is deployed in-cluster, replace the URL with the service's external address.
{
"mcpServers": {
"radar": {
"type": "http",
"url": "http://localhost:9280/mcp"
}
}
}Prompts to try
Use these prompts with an AI client connected to Radar's MCP server to inspect and manage your Kubernetes cluster.
- "Run a cluster audit and summarize the top security findings."
- "Is the 'payment-service' ServiceAccount over-privileged? What can it access?"
- "Show me all cluster audit findings in the production namespace."
- "Sync the ArgoCD application 'frontend' and report its health status."
- "Why are the pods in the checkout deployment in CrashLoopBackOff?"
- "List all RBAC permissions for the 'ci-runner' ServiceAccount."Troubleshooting Radar
Radar cannot connect to the cluster — 'connection refused' or 'unauthorized' errors
Verify your kubeconfig is valid with 'kubectl cluster-info'. Use the --kubeconfig flag to specify an alternate path: 'radar --kubeconfig /path/to/config'. Ensure the kubeconfig context has sufficient RBAC permissions to list pods, events, and services.
The MCP server is not accessible on port 9280
Radar starts the MCP server on the same port as the web UI (default 9280). Confirm Radar is running with 'ps aux | grep radar'. If the port is in use, specify an alternate with '--port 9281'. Check that '--no-mcp' was not accidentally passed.
GitOps tools (manage_gitops) return 'not found' errors
The manage_gitops tool requires FluxCD or ArgoCD to be installed in the cluster. Radar auto-detects these controllers. If detection fails, ensure the flux-system or argocd namespace exists and the controllers are running.
Frequently Asked Questions about Radar
What is Radar?
Radar is a Model Context Protocol (MCP) server that missing open source kubernetes ui. topology, event timeline, and service traffic — plus resource browsing and helm management. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Radar?
Follow the installation instructions on the Radar GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Radar?
Radar works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Radar free to use?
Yes, Radar is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
Radar Alternatives — Similar Cloud Services Servers
Looking for alternatives to Radar? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Open WebUI
★ 138.2kUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
★ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
★ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
★ 33.0kan easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
Xiaozhi ESP32
★ 26.7k本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
Gateway
★ 11.8kA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Browse More Cloud Services MCP Servers
Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Radar in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Radar?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.