mcp-kubernetes-server
mcp-kubernetes-server is an MCP server, listed under version control. It reaches github. Its repository has 20 GitHub stars and is licensed under Apache-2.0; we last read it on 2026-10-22.
This MCP server connects AI assistants to Kubernetes clusters, translating natural language requests into Kubernetes operations and providing results in a format understandable to AI tools.
Install
MCP servers are packaged differently from each other -- some run via npx, some as a Docker image, some as a plain script you clone and run. mcp-kubernetes-server’s own README did not state one plainly enough for this page to quote it rather than guess, so it will not guess. The repository below states it.
What it reaches, and what it needs
What it connects to
Unverified means a mention in the server’s own description, not a citation. A wrong claim here costs nothing to correct and nothing to trust yet.
Maintenance
A Model Context Protocol (MCP) server that enables AI assistants to interact with Kubernetes clusters. It serves as a bridge between AI tools (like Claude, Cursor, and GitHub Copilot) and Kubernetes, translating natural language requests into Kubernetes operations and returning the results in a format the AI tools can understand.
What mcp-kubernetes-server can do
39 tools documented in its README. An AI client calls these by name.
kubectl- Run any kubectl command and return the output
helm- Run any helm command and return the output
k8s_get- Fetch any Kubernetes object (or list) as JSON string
k8s_describe- Show detailed information about a specific resource or group of resources
k8s_logs- Print the logs for a container in a pod
k8s_events- List events in the cluster
k8s_apis- List all available APIs in the Kubernetes cluster
k8s_crds- List all Custom Resource Definitions (CRDs) in the Kubernetes cluster
k8s_top_nodes- Display resource usage (CPU/memory) of nodes
k8s_top_pods- Display resource usage (CPU/memory) of pods
k8s_rollout_status- Get the status of a rollout for a deployment, daemonset, or statefulset
k8s_rollout_history- Get the rollout history for a deployment, daemonset, or statefulset
k8s_auth_can_i- Check whether an action is allowed
k8s_auth_whoami- Show the subject that you are currently authenticated as
k8s_create- Create a Kubernetes resource from YAML/JSON content
k8s_apply- Apply a configuration to a resource by filename or stdin
k8s_expose- Expose a resource as a new Kubernetes service
k8s_run- Create and run a particular image in a pod
k8s_set_resources- Set resource limits and requests for containers
k8s_set_image- Set the image for a container
k8s_set_env- Set environment variables for a container
k8s_rollout_undo- Undo a rollout for a deployment, daemonset, or statefulset
k8s_rollout_restart- Restart a rollout for a deployment, daemonset, or statefulset
k8s_rollout_pause- Pause a rollout for a deployment, daemonset, or statefulset
k8s_rollout_resume- Resume a rollout for a deployment, daemonset, or statefulset
k8s_scale- Scale a resource
k8s_autoscale- Autoscale a deployment, replica set, stateful set, or replication controller
k8s_cordon- Mark a node as unschedulable
k8s_uncordon- Mark a node as schedulable
k8s_drain- Drain a node in preparation for maintenance
k8s_taint- Update the taints on one or more nodes
k8s_untaint- Remove the taints from a node
k8s_exec_command- Execute a command in a container
k8s_port_forward- Forward one or more local ports to a pod
k8s_cp- Copy files and directories to and from containers
k8s_patch- Update fields of a resource
k8s_label- Update the labels on a resource
k8s_annotate- Update the annotations on a resource
k8s_delete- Delete resources by name, label selector, or all resources in a namespace
Read from the README; names are kept only if the README contains them.
mcp-kubernetes-server compared with similar servers
| Server | Reaches | Needs | Stars | Last update | Licence |
|---|---|---|---|---|---|
| mcp-kubernetes-server (this page) | github | None listed | 20 | 2026-02-04 | Apache-2.0 |
| mcp-proxy | github(1 shared) | API_ACCESS_TOKEN, GITHUB_PERSONAL_ACCESS_TOKEN | 2,805 | 2026-10-14 | MIT |
| cve-mcp-server | abuseipdb, github, greynoise, nvd, shodan, urlscan, virustotal, vulncheck(1 shared) | ABUSEIPDB_KEY, GITHUB_TOKEN, GREYNOISE_API_KEY, NVD_API_KEY, SHODAN_KEY, URLSCAN_KEY, VIRUSTOTAL_KEY, VULNCHECK_TOKEN | 1,633 | 2026-10-01 | Apache-2.0 |
| idea-reality-mcp | github(1 shared) | GITHUB_TOKEN | 828 | 2026-09-18 | MIT |
| MarkuprPlus | github(1 shared) | GITHUB_TOKEN | 80 | 2026-10-18 | MIT |
| mcp-bridge-api | github, slack(1 shared) | GITHUB_TOKEN, SLACK_BOT_TOKEN | 69 | 2026-09-18 | NOASSERTION |
Ranked by services in common with mcp-kubernetes-server, then by stars. Figures are from each repository when we last read it.
Common questions about mcp-kubernetes-server
- What does mcp-kubernetes-server do?
- This MCP server connects AI assistants to Kubernetes clusters, translating natural language requests into Kubernetes operations and providing results in a format understandable to AI tools.
- How do I install mcp-kubernetes-server?
- Its README did not state an install command plainly enough for us to quote one, so we do not guess. The repository has the instructions: https://github.com/feiskyer/mcp-kubernetes-server
- What does mcp-kubernetes-server connect to, and what does it need?
- It reaches github.
- Which AI clients can use mcp-kubernetes-server?
- Its own description mentions Cursor. That is a mention in its description, not a test we ran.
- Is mcp-kubernetes-server official and is it maintained?
- We found nothing naming it as a vendor’s official server. Its repository has 20 GitHub stars and its state in our directory is listed. Its last commit we recorded was on 2026-02-04.
- What licence does mcp-kubernetes-server use?
- The repository declares the Apache-2.0 licence.
More MCP servers for version control
- mcp-proxy2,805 stars
- cve-mcp-server1,633 stars
- idea-reality-mcp828 stars
- anythingmcp775 stars
- RepoMapper217 stars
- gitlab-mr-mcp94 stars