Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/mikhae1/kubeview-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/mikhae1/kubeview-mcp/kubeview)<a href="https://agentmods.dev/mcp/mikhae1/kubeview-mcp/kubeview"><img src="https://agentmods.dev/badge/mcp/mikhae1/kubeview-mcp/kubeview/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/mikhae1/kubeview-mcp/kubeview"><img src="https://agentmods.dev/badge/mcp/mikhae1/kubeview-mcp/kubeview.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
kubeview scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"kubeview": {
"command": "npx",
"args": [
"-y",
"kubeview-mcp"
],
"env": {
"KUBECONFIG": "",
"MCP_TRANSPORT": "",
"MCP_MODE": "",
"MCP_CODE_MODE_DISABLED_TOOLS": "",
"MCP_ARGO_TOOLS": "",
"MCP_ARGOCD_TOOLS": "",
"MCP_LOG_LEVEL": "",
"MCP_KUBE_CONTEXT": "",
"MCP_K8S_SKIP_TLS_VERIFY": "",
"MCP_HIDE_SENSITIVE": "",
"MCP_TIMEOUT": "",
"MCP_HTTP_HOST": "",
"MCP_HTTP_PORT": "",
"MCP_HTTP_PATH": "",
"MCP_HTTP_JSON_RESPONSE": "",
"MCP_APPROVAL_STATE_SECRET": "",
"MCP_APPROVAL_REPLAY_DIR": "",
"MCP_ALLOWED_HOSTS": "",
"MCP_ALLOWED_ORIGINS": "",
"KUBE_MCP_FORCE_VM_SANDBOX": "",
"MCP_DISABLE_KUBERNETES_PLUGIN": "",
"MCP_DISABLE_HELM_PLUGIN": "",
"MCP_DISABLE_ARGO_PLUGIN": "",
"MCP_DISABLE_ARGOCD_PLUGIN": ""
}
}
}What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 35 lines scan A 7c7e05c4bdc6
kubeview is an MCP server published in the GitHub repository mikhae1/kubeview-mcp (5 stars, last pushed 7d ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other mcp servers, from other repositories
radar
MCP server "radar" as configured in skyhook-io/radar. Runs in Docker (ghcr.io/skyhook-io/radar:1.9.2).
devops-status-mcp-server
Vendor status pages, TLS cert inspection, DNS propagation checks, and incident-response playbooks. Runs locally from the @cyanheads/devops-status-mcp-server npm package. Needs 3 environment variables to run.
kube-lint-mcp
MCP server for Kubernetes, Helm, ArgoCD, and FluxCD validation. Runs locally from the kube-lint-mcp Python package.
dynadot
MCP server for Dynadot domain registrar — domain search, registration, DNS, and transfers. Runs locally from the dynadot-mcp npm package. Needs 2 environment variables to run.
cloudcostsmcp
MCP server for cloud pricing (AWS, GCP, Azure). Runs locally from the opencloudcosts Python package. Needs 5 environment variables to run.
obambu-cpanel-mcp
MCP server exposing cPanel UAPI (domains, DNS, email, MySQL, files) as tools for AI assistants. Runs locally from the obambu-cpanel-mcp npm package. Needs 4 environment variables to run.