Kubernetes MCP Server (Rajdyp)
Kubernetes cluster operations via read-only Python-based MCP tools.
Data last scanned today · Reviewed today
Overview
The Kubernetes MCP Server provides a bridge between AI models and Kubernetes clusters. It utilizes the official Kubernetes Python client to enable read-only monitoring and inspection tasks within a supported environment. The server is built using fastmcp and organizes its operations by resource types, such as pods, to ensure focused interaction with cluster data. Users require an existing kubeconfig file to establish connectivity and execute operations through the MCP protocol.
Our verdict
With a security score of 24/100, this project is classified as high-risk. This rating is driven primarily by the fact that the server is community-maintained rather than vendor-official and has not undergone editorial review. Potential users should be aware that the repository has had no activity for over 300 days. It is suitable only for non-sensitive local development environments where the user can manually audit the code before execution.
- Utilizes the official Kubernetes Python client library
- Restricts functionality to read-only operations by design
- Minimalist architecture with zero direct dependencies
- High risk score of 24/100 due to lack of maintenance
- Single-contributor project with no recent updates for 326 days
- Authentication methods have not been externally reviewed
Compatibility
| Client | Local | Docker | Remote | Read-only |
|---|---|---|---|---|
| ChatGPT | ||||
| Claude Desktop | ||||
| Cursor | ||||
| VS Code | ||||
| Windsurf |
Frequently asked questions
›What level of access does this server have to my Kubernetes cluster?
The server is restricted to read-only operations for your Kubernetes cluster.
›What are the environment prerequisites for running this server?
You need Python 3.10 or higher, an active kubeconfig file typically located at ~/.kube/config, and valid access to a Kubernetes cluster.
›How can I launch the Kubernetes MCP server?
You can start the server by executing 'python -m k8s_mcp_server.server' or by using 'fastmcp run k8s_mcp_server/server.py'.
Alternatives
Badge
Maintain this server? Add the live badge to your README.