manusa/Kubernetes MCP Server
by Various
Model Context Protocol (MCP) server for Kubernetes and OpenShift
MCP
manusa/Kubernetes MCP Server
Added 1 June 2026
Overview
A Model Context Protocol server that enables AI assistants to interact with Kubernetes and OpenShift clusters. Written in Go, it exposes cluster resources and operations through the MCP interface for tool-based management.
Best for
Best for
Developers and platform engineers who want to manage Kubernetes clusters through conversational AI tools.
Use cases
- Querying and managing Kubernetes pods, deployments, and services via an AI assistant
- Troubleshooting cluster issues by inspecting logs and events through natural language
- Automating routine cluster operations like scaling or rolling updates with AI-driven commands
Notes
A Model Context Protocol server that enables AI assistants to interact with Kubernetes and OpenShift clusters. Written in Go, it exposes cluster resources and operations through the MCP interface for tool-based management.
1,642 stars on GitHub. Last updated 2026-06-01. Licensed Apache-2.0.
Use cases
- Querying and managing Kubernetes pods, deployments, and services via an AI assistant
- Troubleshooting cluster issues by inspecting logs and events through natural language
- Automating routine cluster operations like scaling or rolling updates with AI-driven commands
Pros
- Open source with active development and 1,600+ GitHub stars
- Supports both Kubernetes and OpenShift clusters out of the box
- Integrates with any MCP-compatible AI client (e.g., Claude, custom agents)
Cons
- Requires a running MCP client and network access to the cluster
- Cluster permissions must be configured separately for the server’s service account
- Limited to operations exposed by the MCP protocol; not a full kubectl replacement
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Open source with active development and 1,600+ GitHub stars
- Supports both Kubernetes and OpenShift clusters out of the box
- Integrates with any MCP-compatible AI client (e.g., Claude, custom agents)
Cons
- Requires a running MCP client and network access to the cluster
- Cluster permissions must be configured separately for the server's service account
- Limited to operations exposed by the MCP protocol; not a full kubectl replacement
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.