Read-only Kubernetes diagnostics: pods, logs, events, workloads, services, PVCs and nodes.
Kubernetes Troubleshoot is an MCP integration. Read-only Kubernetes diagnostics: pods, logs, events, workloads, services, PVCs and nodes.
The published oci package is docker.io/yawgyamfiprem32/k8s-troubleshoot-mcp:1.0.0. Its declared MCP transport is stdio.
The package declares KUBECONFIG (required): Path to the kubeconfig inside the container. Must match the mount destination. There is no fallback to ~/.kube/config and no in-cluster config: a missing, unreadable or malformed file is a startup failure rather than a silent downgrade to an ambient credential.; ALLOWED_NAMESPACES (required): Comma-separated namespaces the server may read, e.g. staging,production. Wildcards ( and all) are rejected at startup, and kube-system and kube-public are stripped even if listed. This is defense-in-depth, not the security boundary — the boundary is the ServiceAccount's RBAC bindings.; LOG_LEVEL: DEBUG, INFO, WARNING or ERROR. All logging goes to stderr; stdout carries the JSON-RPC stream exclusively.; API_TIMEOUT_SECONDS: Kubernetes API request timeout. Must be a positive integer.; MAX_LOG_LINES: Maximum log lines any single get_pod_logs call may return. Must be a positive integer; clamped to a hard ceiling of 1000 with a warning..
This package has launch arguments in its registry record. Use the maintainer’s configuration for those arguments rather than launching it with only the package name.
Check the maintainer’s instructions for account access, authentication and the supported client configuration. Once connected, inspect the tools your client receives and try a small task that matches the server’s stated purpose. The registry description does not include a verified, complete tool list.
View the publisher’s registry entry · Project repository · Project website. This profile uses version 1.0.0 from the registry. Registration identifies the publisher namespace; it does not establish that this is a first-party integration for every service it connects.
Browse related cloud & devops MCP servers for tools that cover the same kind of work.
| Variable | Description | Required |
|---|---|---|
| KUBECONFIG | Path to the kubeconfig inside the container. Must match the mount destination. There is no fallback to ~/.kube/config and no in-cluster config: a missing, unreadable or malformed file is a startup failure rather than a silent downgrade to an ambient credential. | Yes |
| ALLOWED_NAMESPACES | Comma-separated namespaces the server may read, e.g. staging,production. Wildcards ( and all) are rejected at startup, and kube-system and kube-public are stripped even if listed. This is defense-in-depth, not the security boundary — the boundary is the ServiceAccount's RBAC bindings. | Yes |
| LOG_LEVEL | DEBUG, INFO, WARNING or ERROR. All logging goes to stderr; stdout carries the JSON-RPC stream exclusively. | Optional |
| API_TIMEOUT_SECONDS | Kubernetes API request timeout. Must be a positive integer. | Optional |
| MAX_LOG_LINES | Maximum log lines any single get_pod_logs call may return. Must be a positive integer; clamped to a hard ceiling of 1000 with a warning. | Optional |
Stop letting your assistant hallucinate n8n node parameters — this server hands it the real schemas, templates and validation.
AWS Labs' official server suite — current AWS docs, CDK guidance, cost analysis and service tools.
Cloud browsers for AI agents — automation sessions that run in Browserbase's fleet, not on your machine.
Workers, KV, R2 and D1 by conversation — Cloudflare's official remote servers for building and observability.
Dashboards, Prometheus and Loki queries, incidents and alerts — observability by conversation.
kubectl with a conversational interface — inspect pods, read logs, diagnose clusters and manage workloads.