Kubernetes Claude

by blankcut

6 stars
Not rated
GitHub

About

Integrates Claude with Kubernetes, ArgoCD, and GitLab to analyze and troubleshoot GitOps workflows by collecting resource information, correlating cross-system data, and providing actionable recommendations through a RESTful API.

Details

Author
blankcut
Repository
Blankcut/kubernetes-mcp-server
GitHub stars
6
License
MIT License
Categories
Developer Tools, Other, AI, Productivity, Design, Workplace, Search, Automation, Communication, Knowledge Base

Jump to

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Kubernetes Claude
    Command (node, npx, python, etc.) npx
    Arguments
    • Argument 1 -y
    • Argument 2 @highlight/mcp-server

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Export credentials for ArgoCD, GitLab, and Claude:

export ARGOCD_USERNAME="argocd-username"

export ARGOCD_PASSWORD="argocd-password"

export GITLAB_TOKEN="gitlab-token"

export CLAUDE_API_KEY="claude-api-key"

export VAULT_TOKEN="optional-if-using-vault"

Ensure a kubeconfig is available:

export KUBECONFIG=~/.kube/config

Update kubernetes-claude-mcp/config.yaml with credentials and server preferences:
```yaml

Health Check

Checks the health status of the server. Method: GET, Endpoint: /api/v1/health

List Namespaces

Retrieves a list of namespaces in the Kubernetes cluster. Method: GET, Endpoint: /api/v1/namespaces

List Resources

Lists resources of a specific kind in a given namespace. Method: GET, Endpoint: /api/v1/resources/{kind}?namespace={ns}

Get Specific Resource

Fetches details of a specific resource by its kind and name within a namespace. Method: GET, Endpoint: /api/v1/resources/{kind}/{name}?namespace={ns}

Get Events for a Resource

Retrieves events associated with a specific resource in a namespace. Method: GET, Endpoint: /api/v1/events?namespace={ns}&resource={kind}&name={name}

List Applications

Lists all applications managed by ArgoCD. Method: GET, Endpoint: /api/v1/argocd/applications

Analyze Resource

Analyzes the specified resource and returns insights. Method: POST, Endpoint: /api/v1/mcp/resource

Troubleshoot Resource

Troubleshoots the specified resource and provides recommendations. Method: POST, Endpoint: /api/v1/mcp/troubleshoot

Commit Analysis (GitLab)

Commits the analysis results to GitLab. Method: POST, Endpoint: /api/v1/mcp/commit

Generic MCP Request

Processes a generic request to the MCP server. Method: POST, Endpoint: /api/v1/mcp

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "kubernetes claude": {
            "env": {},
            "args": [
                "-y",
                "@highlight/mcp-server"
            ],
            "command": "npx"
        }
    }
}

Linux

{
    "env": [],
    "args": [
        "-y",
        "@highlight/mcp-server"
    ],
    "command": "npx"
}

Macos

{
    "env": [],
    "args": [
        "-y",
        "@highlight/mcp-server"
    ],
    "command": "npx"
}

Windows

{
    "env": [],
    "args": [
        "/c",
        "npx",
        "-y",
        "@highlight/mcp-server"
    ],
    "command": "cmd"
}

- List Kubernetes namespaces— Retrieve all namespaces in the cluster viaGET /api/v1/namespaces.
- List resources by kind— Fetch resources of a given kind (pods, deployments, etc.) within a namespace usingGET /api/v1/resources/{kind}.
- Get resource details— Inspect a specific Kubernetes resource by name and namespace withGET /api/v1/resources/{kind}/{name}.
- Retrieve resource events— Query Kubernetes events filtered by namespace, resource kind, and name viaGET /api/v1/events.
- List ArgoCD applications— View all applications managed by ArgoCD throughGET /api/v1/argocd/applications.
- Troubleshoot a resource— Ask the assistant to analyze a failing pod or other resource usingPOST /api/v1/mcp/troubleshoot.

A Model Context Protocol (MCP) server for Kubernetes cluster management with ArgoCD and GitLab integration.

This repository contains the Claude Kubernetes MCP (Model Context Protocol) server, built in Go. The server integrates with ArgoCD, GitLab, Claude AI, and Kubernetes to enable advanced control and automation of Kubernetes environments.

- Overview
- Prerequisites
- Setup Instructions
- Configuration
- Running Locally
- Building and Running with Docker
- Production Deployment
- API Documentation
- Postman Collection
- License

This server is designed to orchestrate Kubernetes workloads using Claude AI, GitLab, ArgoCD, and Vault. It exposes a REST API that allows programmatic interaction with these systems, driven by a configuredconfig.yamland authenticated using an API key.

- Go 1.20+
- Docker
- Kubernetes cluster & valid~/.kube/config
- EKS cluster with AWS_PROFILE set locally
- ArgoCD credentials
- GitLab personal access token
- Claude API key (Anthropic)
- Vault credentials (optional, depending on use)

git clone https://github.com/blankcut/kubernetes-mcp-server.git cd kubernetes-mcp-server

2. Export Required Environment Variables

Export credentials for ArgoCD, GitLab, and Claude:

export ARGOCD_USERNAME="argocd-username" export ARGOCD_PASSWORD="argocd-password" export GITLAB_TOKEN="gitlab-token" export CLAUDE_API_KEY="claude-api-key" export VAULT_TOKEN="optional-if-using-vault"

Updatekubernetes-claude-mcp/config.yamlwith credentials and server preferences:

server: address: ":8080" readTimeout: 30 writeTimeout: 60 auth: apiKey: ""${API_KEY}"" kubernetes: kubeconfig: "" inCluster: false defaultContext: "" defaultNamespace: "default" argocd: url: "http://example.argocd.com" authToken: "" username: "${ARGOCD_USERNAME}" password: "${ARGOCD_PASSWORD}" insecure: true gitlab: url: "https://gitlab.com" authToken: "${AUTH_TOKEN}" apiVersion: "v4" projectPath: ""${PROJECT_PATH}"" claude: apiKey: "${API_KEY}" baseURL: "https://api.anthropic.com" modelID: "claude-sonnet-4.5-20250514" maxTokens: 8192 temperature: 0.3

You can use the provided Go templates or environment variable interpolation method.

Please ensure aconfig.yamlincludes anapiKey. This will be used to authenticate requests in Postman or any external client.

cd kubernetes-claude-mcp go run ./cmd/server/main.go

LOG_LEVEL=debug go run ./cmd/server/main.go --config config.yaml

Server will start and bind to the configured port inconfig.yaml(default: 8080).

cd kubernetes-claude-mcp docker build -t claude-mcp-server -f Dockerfile .

2. Run the Container (second build option included)

cd kubernetes-claude-mcp docker-compose build docker-compose up -d

A Helm chart is included in the repository for Kubernetes deployment:

cd kubernetes-claude-mcp/deployments/helm

Updatevalues.yamlwith appropriate values and run:

Please ensure secrets and config maps are properly mounted and secured in the cluster.

Below are the primary endpoints exposed by the MCP server. All requests require theX-API-Keyheader:

- GET /api/v1/resources/{kind}?namespace={ns}

- GET /api/v1/resources/{kind}/{name}?namespace={ns}

- GET /api/v1/events?namespace={ns}&resource={kind}&name={name}

- List Applications

- GET /api/v1/argocd/applications

- Analyze Resource

- POST /api/v1/mcp/resource

All POST endpoints accept a JSON payload containing fields such as:

{ "resource": "pod", "name": "example-pod", "namespace": "default", "query": "What’s wrong with this pod?" }

A ready-to-use Postman collection will be available soon.

Please contribute to our coffee fund to help us continue to do great thingsBuy Me Coffee

This project is licensed under theMIT License.

Documentation will be expanded soon. If you’d like to contribute, feel free to open a pull request or file an issue!

The all-seeing guardian for macOS: Battery, Clipboard, TTS, and File System control using Claude desktop

A Model Context Protocol (MCP) server that provides AI assistants (like Claude) with tools to directly interact with PostgreSQL databases securely.

Deterministic code-graph (GraphRAG) over your repo for LLM agents — local-first, git-native, zero-infra, served via MCP.

Persistent memory for any AI assistant. Zero token cost until recall. Stores memories in local SQLite, ranks by 6-factor scoring, returns results 79% smaller than JSON. Works with Claude, ChatGPT, Grok, Cursor, Windsurf, and any MCP client.

An MCP server for AI video generation. MCP server for AI video generation. Lets Claude, ChatGPT, OpenClaw , Hermes & other agents create AI videos and publish them to YouTube, TikTok, Instagram etc..

Secure audio transcription meets AI. Connect Alice recordings to Claude, ChatGPT, Gemini, and more.

The DataFast MCP server lets MCP-compatible clients such as Codex, Claude Code, and Cursor query your analytics and manage your account through natural language.

Eagle MCP Server is a local Model Context Protocol bridge that lets AI assistants (e.g. Cursor, Claude) access your Eagle media library so you can tag, categorize, search, and batch-organize assets with natural language.

HumanDesign.ai MCP is the official account-connected Human Design server for Claude, ChatGPT, Codex, Cursor, and VS Code.

Inkrun's remote MCP server lets AI agents like Claude turn Markdown into themed, consistent and reproducible on-brand PDFs with a single tool call

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

Install

Add to Claude Desktop or Cursor

{
    "mcpServers": {
        "kubernetes claude": {
            "env": {},
            "args": [
                "-y",
                "@highlight/mcp-server"
            ],
            "command": "npx"
        }
    }
}

More like this

Similar MCP servers you might find useful

Browse category

Sequential Thinking

Sequential Thinking is an MCP server that provides a tool for dynamic and reflective problem-solving through a structured, step-by-step thinking process. It is…

88.2k
Other

Filesystem

Filesystem is a Node.js server that implements the Model Context Protocol (MCP) for filesystem operations. It enables AI assistants to read, write, and manage…

88.1k
Other