
Mcp K8s Ro
Gives Claude read-only access to your Kubernetes clusters through kubectl-style operations: list resources, describe objects, tail logs, check events, and pull metrics from metrics-server. Built in Go over stdio. Secrets are automatically masked before they reach the model, and the server locks to whatever kubeconfig context is active at startup, so prompt injection can't make Claude pivot to production. Responses are token-efficient, returning only diagnostic fields instead of full API objects. When Claude wants to mutate something, it prints the kubectl command for you to run manually. If you troubleshoot Kubernetes incidents with an AI and want guardrails that work even when you're tired, this handles the inspection layer safely.
- GitHub stars
- 1
- tools
- 7
- transport
- STDIO
- env var
- 1
- last updated
- Oct 30, 2026
Tools
7 toolsPublic tool metadata for what this MCP can expose to an agent.
k8s_list_resourcesList any resource type by name — pods, deployments, CRDs, etc. Accepts optional namespace filter. Returns name, status, readiness, restarts, node, IP, and more depending on resource kind.
List any resource type by name — pods, deployments, CRDs, etc. Accepts optional namespace filter. Returns name, status, readiness, restarts, node, IP, and more depending on resource kind.
No parameter schema in public metadata yet.
k8s_describe_resourceReturn the full YAML of a single resource. Secret data is masked.
Return the full YAML of a single resource. Secret data is masked.
No parameter schema in public metadata yet.
k8s_list_resource_typesList all available resource types via the discovery API. Accepts optional API group filter.
List all available resource types via the discovery API. Accepts optional API group filter.
No parameter schema in public metadata yet.
k8s_get_logsFetch pod logs. Supports container selector, tail lines, and `--previous` for crashed containers.
Fetch pod logs. Supports container selector, tail lines, and `--previous` for crashed containers.
No parameter schema in public metadata yet.
k8s_get_eventsList Kubernetes events for a namespace or the whole cluster, sorted by most recent.
List Kubernetes events for a namespace or the whole cluster, sorted by most recent.
No parameter schema in public metadata yet.
k8s_top_podsCPU and memory usage per pod, with per-container breakdown. Requires metrics-server.
CPU and memory usage per pod, with per-container breakdown. Requires metrics-server.
No parameter schema in public metadata yet.
k8s_top_nodesCPU and memory usage per node, with percentage of allocatable capacity. Requires metrics-server.
CPU and memory usage per node, with percentage of allocatable capacity. Requires metrics-server.
No parameter schema in public metadata yet.
Sponsors
Configuration
KUBECONFIGPath to the kubeconfig file. Defaults to ~/.kube/config.
Readme
mcp-k8s-ro
A read-only MCP server that gives Claude access to Kubernetes clusters. Built in Go, it communicates over stdio using the MCP protocol.
Design
Details
- Repository
- github.com/your-ko/mcp-k8s-ro
- Category
- Cloud & Infrastructure
- Package
ghcr.io/your-ko/mcp-k8s-ro:1.2.2- Transport
- STDIO
- Registry
- MCP registry, active