Server providing Argo CD integration for MCP clients.
Clusterport 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.
What it does
Core kubectl operations: get, describe, logs, apply, scale, patch, rollout and explain.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user clusterport-mcp '--' npx -y @reneturcios/clusterport mcp
# 2 — ask your agent for something these tools do
# kubectl_get, kubectl_describe, kubectl_logs and 9 more
Clusterport costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
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 Clusterport 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 is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user clusterport-mcp '--' npx -y @reneturcios/clusterport mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
12 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Get Kubernetes resources with kubectl get, as JSON by default.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| resource_type | string | yes | Kubernetes resource type to get, such as pods, deployments, or services. |
| name | string | no | Name of the specific resource to get; when omitted, all resources of the type are listed. |
| namespace | string | no | Namespace of the resource to get; when omitted, the current-context default namespace is used. |
| output_format | string | no | Output format for kubectl get, such as json or yaml; defaults to json. |
Describe one Kubernetes resource with kubectl describe.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| resource_type | string | yes | Kubernetes resource type to describe, such as pod, deployment, or service. |
| name | string | yes | Name of the resource to describe. |
| namespace | string | no | Namespace of the resource to describe; when omitted, the current-context default namespace is used. |
Fetch logs from a Kubernetes pod with kubectl logs.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | Name of the pod to fetch logs from. |
| namespace | string | no | Namespace of the pod; when omitted, the current-context default namespace is used. |
| container | string | no | Container name within the pod to fetch logs from, for pods with multiple containers. |
Apply a manifest with kubectl apply, sent over stdin.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| manifest | string | yes | Kubernetes manifest content to apply, sent to kubectl apply over stdin. |
| namespace | string | no | Namespace to apply the manifest into; when omitted, the manifest or default namespace is used. |
| dry_run | boolean | no | When true, run as a client-side dry run without persisting any changes. |
Create a resource from a generated manifest spec, sent over stdin.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| resource_type | string | yes | Kubernetes resource type to create, such as deployment or pod. |
| name | string | yes | Name for the resource to create. |
| namespace | string | no | Namespace to create the resource in; when omitted, no namespace is set in the generated manifest. |
| image | string | no | Container image to use in the generated manifest; defaults to the resource name when omitted. |
Delete one Kubernetes resource with kubectl delete.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| resource_type | string | yes | Kubernetes resource type to delete, such as pod, deployment, or service. |
| name | string | yes | Name of the resource to delete. |
| namespace | string | no | Namespace of the resource to delete; when omitted, the current-context default namespace is used. |
Scale a workload with kubectl scale.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| resource_type | string | yes | Kubernetes resource type to scale, such as deployment or replicaset. |
| name | string | yes | Name of the workload to scale. |
| namespace | string | no | Namespace of the workload to scale; when omitted, the current-context default namespace is used. |
| replicas | number | yes | Number of replicas to scale the workload to. |
Patch one Kubernetes resource with kubectl patch.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| resource_type | string | yes | Kubernetes resource type to patch, such as deployment or service. |
| name | string | yes | Name of the resource to patch. |
| namespace | string | no | Namespace of the resource to patch; when omitted, the current-context default namespace is used. |
| patch | string | yes | Patch content to apply to the resource, passed to kubectl patch with -p. |
Run a kubectl rollout action (status, history, restart, undo, pause, resume).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| resource_type | string | yes | Kubernetes resource type for the rollout, such as deployment. |
| name | string | yes | Name of the resource to run the rollout action on. |
| namespace | string | no | Namespace of the resource; when omitted, the current-context default namespace is used. |
| action | string | yes | Rollout action to run: status, history, restart, undo, pause, or resume. |
Read or switch the kubectl context (current, list, use).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| operation | string | yes | Context operation to perform: current, list, or use. |
| name | string | no | Name of the context to switch to; required when the operation is use. |
Explain a Kubernetes resource schema with kubectl explain.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| resource | string | yes | Kubernetes resource or field path to explain, such as pod or pod.spec.containers. |
| api_version | string | no | API version to explain the resource against, passed as --api-version; when omitted, the default version is used. |
List the API resources the cluster serves, optionally filtered by kind.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| kind | string | no | Kind to filter the API resource list by, matched case-insensitively; when omitted, all resources are listed. |
- 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 Clusterport or to call it, at any volume.
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.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
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.
Tools were statically extracted from the published source (12 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
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. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| kubectl_get | no tags | |
| kubectl_describe | no tags | |
| kubectl_logs | untrusted-input | untrusted-input: keyword "fetch" |
| kubectl_apply | no tags | |
| kubectl_create | no tags | |
| kubectl_delete | no tags | |
| kubectl_scale | no tags | |
| kubectl_patch | no tags | |
| kubectl_rollout | no tags | |
| kubectl_context | no tags | |
| explain_resource | no tags | |
| list_api_resources | no tags |
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
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
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.1.0. Pin a release below and the command asks for exactly that one.
No release note was published with this version.
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.
Any signed-in account that does not publish Clusterport can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
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.