radar
The missing open-source Kubernetes UI with a built-in MCP server for AI agents. See what's broken, why, and what changed. Issues, Topology, event timeline, Helm, GitOps, live service traffic, and cluster audits - all in one Go binary.
Radar is an open-source Kubernetes UI with an integrated Model Context Protocol (MCP) server that exposes cluster observability and operations to AI agents like Claude, Cursor, and Copilot. Instead of raw kubectl YAML output, AI assistants receive pre-processed, token-optimized data including topology graphs, health assessments, deduplicated events, and filtered logs. The MCP server provides read-only diagnosis by default, with optional write operations (restart, scale, apply, rollback) subject to Kubernetes RBAC. It runs as a single Go binary locally or in-cluster, requiring no account or cloud backend.
Key Features
Use Cases
- 01Enable AI assistants to investigate Kubernetes cluster issues and provide diagnostic insights
- 02Allow AI agents to explain resource relationships, pod failures, and configuration drift
- 03Automate cluster operations through AI-driven scaling, rollbacks, and deployments with RBAC enforcement
- 04Debug CrashLoopBackOff, ImagePullBackOff, and other pod issues with AI-assisted analysis
- 05Analyze Helm releases, GitOps sync status, and service mesh traffic patterns through AI queries
- 06Perform pre-upgrade compatibility checks and RBAC permission analysis via AI assistants
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
radar — FAQ
What is the Radar MCP server?+
Radar is a Kubernetes UI that includes a built-in Model Context Protocol (MCP) server, allowing AI agents like Claude and Cursor to inspect and operate your cluster through pre-processed, token-optimized context instead of raw kubectl output.
How do I install and connect Radar to my AI client?+
Install Radar via curl, Homebrew, or download from GitHub releases, then configure your MCP client (Claude Desktop, Cursor, etc.) to connect to Radar's MCP server endpoint. Radar runs locally by default and connects to your cluster using your existing kubeconfig credentials.
Which AI clients work with Radar's MCP server?+
Radar's MCP server works with Claude Desktop, Cursor, GitHub Copilot, and other MCP-compatible AI assistants. See the MCP documentation for client-specific setup instructions.
Do I need API keys or a cloud account?+
No API keys or accounts are required for Radar itself. It uses your existing Kubernetes credentials from kubeconfig and keeps all cluster data local by default. You will need API keys for your chosen AI client to interact with the MCP server.
Is Radar free to use?+
Yes, Radar is fully open source under the Apache 2.0 license and free forever. The complete feature set is available in the OSS version.
Can AI agents perform write operations through Radar?+
Yes, with user confirmation. The MCP server exposes write operations like restart, scale, apply, and rollback, all enforced through Kubernetes RBAC. Diagnosis and inspection are read-only by default.
How do I install radar?+
Open the source repository on GitHub and follow its README. radar is a mcp server — MCP Agents Market links you directly to the official repo.
Is radar free?+
radar is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.