Guardrails for AI agents on your cluster. kubeleash is a local
server for Kubernetes whose
differentiator is RBAC-style, access control. Point it at a
kubeconfig — even a cluster-admin one — and a local policy file constrains what
the agent can actually do, , with destructive actions gated
.
Kubernetes MCP server with RBAC-style, context-scoped guardrails for AI agents.
Install launches the local kubeleash binary — get it via brew, go install, or the container (see Install). VS Code installs in one click; Cursor & Claude open the setup steps (GitHub strips the cursor:// one-click link, so it lives there as copy-paste).
Why
Most Kubernetes MCP servers inherit the kubeconfig's permissions wholesale —
whatever the credentials grant, the agent can do. kubeleash adds three things
native RBAC can't express for this use case:
Constrain the agent independently of the credentials. Effective access is
always kubeconfig-grants ∩ policy-allows — kubeleash only ever subtracts.
Context-aware guardrails. Policy varies by context (prod vs staging vs
dev); native RBAC is per-cluster.
Block destructive verbs (delete/exec/…) as a safety net against agent
mistakes and prompt injection.
What kubeleash enforces
kubeleash governs only the calls routed through it. It provides a hard
guarantee when it is the agent's sole path to the cluster. An agent that also
has shell access (raw kubectl, oc, the API) can step around it, so in a
shell-enabled assistant kubeleash is advisory — pair it with the
using-kubeleash skill, which instructs the agent to stop (not reach for
kubectl) when the leash is unavailable.
Policy in 10 seconds
policies:
- contexts: ".*prod.*" # regex over the active context name
allow:
resources: ["*"]
verbs: [get, list, watch] # read-only in prod
deny:
verbs: [exec] # never, regardless of credentials
Deny wins. Default deny. A broken policy refuses to start — it never fails open.
See examples/policy.yaml for a fuller, commented policy
(read-only prod, broader staging, namespace-scoped dev).
Quickstart
Install it (Homebrew shown — see Install for go install and the
container), then exercise a policy without touching any cluster:
brew install kubeleash/tap/kubeleash
# Grab the commented example policy:
curl -fsSL https://raw.githubusercontent.com/kubeleash/kubeleash/main/examples/policy.yaml -o policy.yaml
# See how kubeleash validates and normalizes a policy (no cluster needed):
kubeleash --policy policy.yaml --print-effective-policy
# Try it without touching any cluster — every decision is logged, nothing runs:
kubeleash --policy policy.yaml --dry-run
Prefer source? git clone https://github.com/kubeleash/kubeleash && cd kubeleash && go build -o kubeleash ./cmd/kubeleash (Go 1.26+).
Then point an MCP client at it (see below). kubeleash
speaks MCP over stdio, so it's launched by your client, not run as a daemon.
Flag
Purpose
--policy <path>
Policy file. Required (or set K8S_MCP_POLICY); with neither, kubeleash refuses to start — default-deny never fails open.
--kubeconfig <path>
Explicit kubeconfig. Omit to use the standard client-go rules ($KUBECONFIG, ~/.kube/config).
--dry-run
Evaluate + log every decision, but never execute against a cluster.
--print-effective-policy
Print the resolved/normalized rules and exit.
--log-level <level>
debug / info / warn / error (default info). The audit log is JSON on stderr (stdout is the MCP transport).
--version
Print version, commit, and build date.
Install
All channels run kubeleash locally over stdio — your client launches the
binary; nothing is hosted. kubeleash is listed in the
official MCP Registry as
io.github.kubeleash/kubeleash, so registry-aware clients can discover it too.
One-click
The Add to Cursor / VS Code buttons
at the top are the fastest path (they need
the kubeleash binary on PATH — see Manual). Other clients:
Claude Code — this repo is its own plugin marketplace:
No separate install step: on first run the plugin uses a kubeleash already on
your PATH, or otherwise downloads the matching release binary (verifying its
checksum) and caches it.
Safe by default — no policy authoring required first: if you have no policy at
~/.kubeleash/policy.yaml, the plugin writes a read-only starter there on
first run (allow get/list/watch, deny exec/delete). Review and widen
it to grant more access. (This convenience is the plugin's only; the raw binary
still requires an explicit --policy and refuses to start without one.)
The plugin also ships two skills — using-kubeleash (how an agent should query
and act through the gated tools) and authoring-kubeleash-policy (how to write
the policy) — so the agent understands the guardrails, not just the tool list.
Claude Desktop — download kubeleash.mcpb from the
releases page and
double-click it; the bundle ships the binary and prompts you for the policy and
kubeconfig.
Cursor (can't prompt — edit the placeholder path afterward in Settings → MCP).
Decodes to {"command":"kubeleash","args":["--policy","/absolute/path/to/policy.yaml"]}:
# Homebrew
brew install kubeleash/tap/kubeleash
# Go
go install github.com/kubeleash/kubeleash/cmd/kubeleash@latest
# Container (great for running the MCP server sandboxed)
docker run --rm -i -v ~/.kube:/root/.kube:ro -v ./policy.yaml:/policy.yaml:ro \
ghcr.io/kubeleash/kubeleash --policy /policy.yaml
kubeleash runs locally over stdio and talks only to your clusters. There
is intentionally no remote/hosted URL connector — it would mean handing
your cluster credentials to a third party.
Use it as an MCP server
kubeleash exposes 8 generic, GVK-agnostic tools (k8s_list, k8s_get,
k8s_apply, k8s_delete, k8s_logs, k8s_exec, k8s_scale, and
k8s_capabilities) that work for any resource, including CRDs. Every call is
checked against your policy and recorded to a JSON audit log on stderr (stdout
is the MCP transport). It speaks MCP over stdio — point your client at the
binary (or container):
Zero telemetry. No phone-home. Local-only by design. kubeleash talks only to
the Kubernetes API servers you point it at — there is intentionally no remote or
hosted connector to route your cluster credentials through. That's a feature, not
a gap: you run it against real clusters with privileged credentials, so nothing
should sit between the agent and your API server but the leash.
अभी टूल सूची नहीं है। रिमोट सर्वर को पहले हेल्थ चेक के बाद सूची मिलती है।
FAQ
सवाल
Kubeleash कैसे इंस्टॉल करें?
इस पेज पर Cursor, Claude Desktop, Claude Code या VS Code के लिए stdio कॉन्फ़िग कॉपी करें। यह पब्लिशर का इंस्टॉल इस्तेमाल करता है, PlugMCP प्रॉक्सी नहीं।
क्या Kubeleash के लिए API key चाहिए?
इस रिकॉर्ड में कोई ज़रूरी एनवायरनमेंट वेरिएबल दर्ज नहीं है।
Kubeleash कौन सा ट्रांसपोर्ट इस्तेमाल करता है?
Kubeleash stdio पर लोकल चलता है।
Kubeleash की पिछली जाँच कब हुई थी?
पिछली जाँच 2026-11-09 को हुई। Kubernetes MCP server with RBAC-style, context-scoped guardrails for AI agents.