Kubernetes Mcp

Created By
HSn0918a year ago
Overview

what is Kubernetes-MCP?

Kubernetes-MCP is a Model Capable Protocol (MCP) server implementation designed in Go for interacting with Kubernetes clusters, allowing MCP-compatible clients to perform Kubernetes operations through defined tools.

how to use Kubernetes-MCP?

To use Kubernetes-MCP, you can start the server using standard I/O or Server-Sent Events (SSE) transport methods. You can also build it from source or use Docker to run the server.

key features of Kubernetes-MCP?

  • Implements the mcp-go library for MCP functionality.
  • Interacts with Kubernetes clusters using the controller-runtime client.
  • Supports multiple transport methods (stdio and SSE).
  • Provides human-readable text and structured JSON output.
  • Implements various Kubernetes API groups for resource management.

use cases of Kubernetes-MCP?

  1. Managing Kubernetes resources like Pods, Deployments, and Services.
  2. Automating Kubernetes operations through MCP-compatible clients.
  3. Facilitating cluster information retrieval and resource management.

FAQ from Kubernetes-MCP?

  • What programming language is Kubernetes-MCP written in?

Kubernetes-MCP is implemented in Go.

  • How can I run Kubernetes-MCP?

You can run it using Docker or build it from source using Go.

  • What transport methods does Kubernetes-MCP support?

It supports standard I/O and Server-Sent Events (SSE) for communication.

Server Config

{
  "mcpServers": {
    "kubernetes-mcp": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-p",
        "8080:8080",
        "-v",
        "~/.kube:/root/.kube",
        "kubernetes-mcp:latest",
        "server",
        "--transport=sse"
      ],
      "env": {
        "KUBECONFIG": "/root/.kube/config"
      }
    }
  }
}
Project Info
Created At
a year ago
Updated At
a year ago
Author Name
HSn0918
Star
-
Language
-
License
-

Recommend Servers

View All
Tavily Mcp
@tavily-ai

JavaScript
a year ago
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