Kubernetes MCP Server

Created By
basebandita year ago
An MCP Server for Kubernetes
Overview

What is Kubernetes MCP Server?

The Kubernetes MCP Server is a Model Context Protocol (MCP) server designed to manage Kubernetes resources through large language models (LLMs) like Claude, allowing users to interact with Kubernetes clusters using natural language.

How to use Kubernetes MCP Server?

To use the Kubernetes MCP Server, install it by running go install github.com/basebandit/kai/cmd/kai, and integrate it with Claude for Desktop by editing the claude_desktop_config.json file to include the server command.

Key features of Kubernetes MCP Server?

  • Cluster Management: Connect to multiple Kubernetes clusters and switch contexts.
  • Resource Operations: Create, read, update, and delete Kubernetes resources.
  • Pod Management: List pods, get details, stream logs, and delete pods.
  • Deployment Management: Create and manage deployments across namespaces.
  • Service Operations: Interact with Kubernetes services.
  • YAML Support: Apply Kubernetes manifests directly from YAML.
  • Custom Resource Support: Work with custom resource definitions (CRDs).

Use cases of Kubernetes MCP Server?

  1. Managing Kubernetes resources through natural language queries.
  2. Automating deployment processes in Kubernetes clusters.
  3. Simplifying the management of multiple Kubernetes clusters.

FAQ from Kubernetes MCP Server?

  • Can I manage multiple Kubernetes clusters?

Yes! The server allows you to connect to and manage multiple clusters.

  • Is there support for custom resources?

Yes! The server supports custom resource definitions (CRDs).

  • How do I install the server?

You can install it by running go install github.com/basebandit/kai/cmd/kai.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
basebandit
Star
15
Language
Go
License
MIT license

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago