mcp-k8s

Created By
silencepera year ago
A Kubernetes MCP (Model Control Protocol) server that enables interaction with Kubernetes clusters through MCP tools.
Overview

what is Mcp K8s?

Mcp K8s is a Kubernetes Model Control Protocol (MCP) server that facilitates interaction with Kubernetes clusters through various MCP tools.

how to use Mcp K8s?

To use Mcp K8s, clone the repository, build the project, and run the server with the appropriate kubeconfig path. You can enable or disable write operations as needed.

key features of Mcp K8s?

  • Query supported Kubernetes resource types (including built-in resources and CRDs)
  • Perform CRUD operations on Kubernetes resources with configurable options
  • Connect to Kubernetes clusters using kubeconfig

use cases of Mcp K8s?

  1. Manage Kubernetes resources through natural language interaction with LLM.
  2. Serve as an intelligent assistant for daily cluster management tasks.
  3. Simplify test environment resource management for developers.
  4. Provide interactive learning for newcomers to Kubernetes.

FAQ from Mcp K8s?

  • Can Mcp K8s manage all Kubernetes resources?

Yes! Mcp K8s can manage both built-in resources and custom resource definitions (CRDs).

  • Is Mcp K8s free to use?

Yes! Mcp K8s is open-source and free to use for everyone.

  • How secure is Mcp K8s?

Mcp K8s implements strict controls for write operations and uses RBAC to ensure necessary permissions.

Server Config

{
  "mcpServers": {
    "mcp-k8s": {
      "command": "mcp-k8s",
      "args": [
        "-kubeconfig",
        "/Users/demo/.kube/config",
        "-enable-create",
        "-enable-delete",
        "-enable-update"
      ]
    }
  }
}
Project Info
Created At
a year ago
Updated At
a year ago
Author Name
silenceper
Star
97
Language
Go
License
Apache-2.0 license

Recommend Servers

View All
Voyei

6 hours ago
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

16 hours ago