Server providing Argo CD integration for MCP clients.
Nothing to run from here
K8s MCP Server (Go) is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
91/100
trust score
38
tools declared
local
runs on your machine
1k
downloads
What it does
Safe Kubernetes access for AI agents via MCP. Read-only by default, with explicit permission modes.
Quickstart
This one is not published to a package registry, so there is no one-line install: it is built and started the way its own source says.
Publishernot claimed
KAAll 1 server
kaneg1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts K8s MCP Server (Go) as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
This one is not published to a package registry, so there is no one-line install: it is built and started the way its own source says.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
[READONLY] Show MCP server version, mode, Kubernetes config source, and runtime details
No parameter schema on file.
[READONLY] Resolve an application/workload name to matching Pod, Service, Deployment, and StatefulSet resources, with suggested next tools
No parameter schema on file.
[READONLY] List pods with status, readiness, restarts, and age. Use all_namespaces=true to list across all namespaces.
No parameter schema on file.
[READONLY] Get detailed information about a specific pod including containers, status, and conditions
No parameter schema on file.
[READONLY] Get logs from a pod. Supports container selection, tail lines, and previous instance
No parameter schema on file.
[READONLY] List services with type, cluster IP, external IP, and ports. Use all_namespaces=true to list across all namespaces.
No parameter schema on file.
[READONLY] Get detailed information about a service including ports, selectors, and endpoints
No parameter schema on file.
[READONLY] List deployments with replica status. Use all_namespaces=true to list across all namespaces.
No parameter schema on file.
[READONLY] Get detailed deployment info including replica status, strategy, containers, and conditions
No parameter schema on file.
[READONLY] List StatefulSets with replica status. Use all_namespaces=true to list across all namespaces.
No parameter schema on file.
[READONLY] Get detailed StatefulSet info including replica status, update strategy, and containers
No parameter schema on file.
[READONLY] List all Kubernetes namespaces with status and age
No parameter schema on file.
[READONLY] Get current CPU and memory usage for cluster nodes via metrics.k8s.io
No parameter schema on file.
[READONLY] List all cluster nodes with status, roles, version, and OS info
No parameter schema on file.
[READONLY] Get a high-level cluster overview: node health, pod counts, resource summary, and problem pods
No parameter schema on file.
[READONLY] Get current CPU and memory usage for pods via metrics.k8s.io
No parameter schema on file.
[READONLY] List Kubernetes events, optionally filtered by namespace, kind, and name
No parameter schema on file.
[READONLY] List ConfigMaps. Use all_namespaces=true to list across all namespaces.
No parameter schema on file.
[READONLY] Get detailed ConfigMap data
No parameter schema on file.
[READONLY] List Secrets (keys only, no values). Use all_namespaces=true to list across all namespaces.
No parameter schema on file.
[READONLY] Get Secret metadata and keys. Values shown only in dangerous mode with show_values=true
No parameter schema on file.
[READONLY] List PersistentVolumeClaims. Use all_namespaces=true to list across all namespaces.
No parameter schema on file.
[READONLY] List Ingress resources. Use all_namespaces=true to list across all namespaces.
No parameter schema on file.
[READONLY] List Jobs. Use all_namespaces=true to list across all namespaces.
No parameter schema on file.
[READWRITE] Restart a deployment (kubectl rollout restart). Triggers rolling update.
No parameter schema on file.
[READWRITE] Restart a statefulset (kubectl rollout restart). Triggers rolling update.
No parameter schema on file.
[READWRITE] Scale a deployment to specified number of replicas
No parameter schema on file.
[READWRITE] Update container image in a deployment
No parameter schema on file.
[READWRITE] Check rollout status of a deployment
No parameter schema on file.
[READWRITE] Create a new namespace
No parameter schema on file.
[READWRITE] Apply a strategic merge patch to a deployment
No parameter schema on file.
[DANGEROUS] Delete a pod. Use with caution!
No parameter schema on file.
[DANGEROUS] Delete a namespace and ALL resources within it!
No parameter schema on file.
[DANGEROUS] Delete a deployment and its pods
No parameter schema on file.
[DANGEROUS] Delete a StatefulSet and its pods
No parameter schema on file.
[DANGEROUS] Delete a DaemonSet and its pods
No parameter schema on file.
No parameter schema on file.
[DANGEROUS] Apply arbitrary YAML manifest. Handles single or multi-document YAML.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install K8s MCP Server (Go) or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 91 / 100
Release 0.4.6 · scanned 14 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score91
Findings1 threat · 0 capability
Capabilityminimal
Coveragemetadata
Verificationrepo
Surface digest2dc22d3bf39daa3966da07121ef3ae7218597d0cc75600bd6ac9471b4c82a657
Score vectorthreat 100 → client 91
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | metadata | inspection depth (metadata) — how much of the target the scan could see | −8 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfacenot available
Implementation sourcenot available
Package metadataread
Live transportnot available
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
The implementation source was not read — the published package was fetched but contains no source files the scanner reads.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
No tool surface was enumerated, so there is nothing to attribute a capability to.
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest2dc22d3bf39daa39
Scanned2026-10-14
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
It installs from its repository rather than from a versioned package, so the command cannot be pinned to a release. The history below is for reading; the current release on file is 0.4.6.
0.4.6
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish K8s MCP Server (Go) can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.