MCPgee
MCPgee
MCPgeeMCPgee

Kagent

v1.0.0•Cloud Services•stable

Cloud Native Agentic AI | Discord: https://bit.ly/kagentdiscord

agentsaicncfdevopsmcp
Share:
2,819
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Kagent?

Kagent is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to cloud native agentic ai | discord: https://bit.ly/kagentdiscord

Cloud Native Agentic AI | Discord: https://bit.ly/kagentdiscord

This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Cloud Native Agentic AI | Discord: https://bit.ly/kagentdisc

Use Cases

Cloud-native agentic AI platform
CNCF-aligned DevOps and agent management
kagent-dev

Maintainer

LicenseApache-2.0
Languagego
Versionv1.0.0
UpdatedMay 22, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx kagent

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Kagent

Kagent is a cloud-native AI agent platform built on Kubernetes that lets teams deploy, manage, and orchestrate AI agents using familiar Kubernetes primitives — custom resources, Helm charts, and kubectl. It ships with a built-in MCP server providing tools for Kubernetes, Istio, Helm, Argo, Prometheus, Grafana, Cilium, and other CNCF-ecosystem components, enabling agents to inspect, configure, and operate infrastructure through natural language. Platform engineers and SREs use it to automate cluster operations, runbook execution, and observability queries without writing custom automation scripts.

Prerequisites

  • A Kubernetes cluster (local via kind/minikube or a cloud provider like EKS/GKE/AKS)
  • kubectl configured to access the target cluster
  • Helm 3.x installed for chart-based deployment
  • An LLM provider API key: OPENAI_API_KEY, ANTHROPIC_API_KEY, or GEMINI_API_KEY
  • An MCP client such as Claude Desktop or Claude Code to interact with the kagent MCP server
1

Install the kagent CLI via Homebrew

The quickest way to get started on macOS or Linux is via Homebrew. The CLI manages installation, upgrades, and agent interaction.

brew install kagent
2

Set your LLM provider API key

Export the API key for whichever LLM provider you want kagent to use. OpenAI is the default but Anthropic, Gemini, Azure OpenAI, and Ollama are also supported.

export OPENAI_API_KEY="your-api-key-here"
3

Install kagent into your cluster

Deploy the kagent controller, engine, and UI into a dedicated namespace using the demo profile. This also installs the built-in MCP server (kmcp) with Kubernetes tools.

kagent install --profile demo
4

Access the kagent dashboard

Open the web UI to create and manage agents, inspect tool calls, and review agent traces.

kagent dashboard
5

Configure your MCP client to connect to kagent

Point your Claude Desktop or Claude Code config to the kagent MCP server. By default the MCP server is accessible via the kagent CLI proxy.

{
  "mcpServers": {
    "kagent": {
      "command": "kagent",
      "args": ["mcp", "serve"],
      "env": {
        "OPENAI_API_KEY": "your-api-key-here"
      }
    }
  }
}
6

Deploy via Helm for production clusters

For production or GitOps-based deployments, use the Helm charts directly. Pass your LLM provider choice and any custom values.

helm install kagent-crds oci://ghcr.io/kagent-dev/kagent/helm/kagent-crds \
  --namespace kagent --create-namespace

helm install kagent oci://ghcr.io/kagent-dev/kagent/helm/kagent \
  --namespace kagent --set providers.default=openAI

Kagent Examples

Client configuration

Claude Desktop configuration connecting to the kagent MCP server via the kagent CLI. Set your actual API key in the env block.

{
  "mcpServers": {
    "kagent": {
      "command": "kagent",
      "args": ["mcp", "serve"],
      "env": {
        "OPENAI_API_KEY": "sk-your-key-here",
        "LOG_LEVEL": "info"
      }
    }
  }
}

Prompts to try

These prompts exercise kagent's built-in Kubernetes and observability tools.

- "List all pods in the default namespace and show which ones are not Running"
- "Check Prometheus for any firing alerts in the last 30 minutes"
- "Describe the Istio virtual service configuration for the payments service"
- "Install the nginx-ingress Helm chart into the ingress namespace"
- "Show me the resource usage (CPU and memory) for all nodes in the cluster"

Troubleshooting Kagent

kagent install fails with 'unable to connect to cluster'

Verify that kubectl is configured for the target cluster by running `kubectl get nodes`. If using a local cluster, ensure kind or minikube is running first.

Agents return 'LLM provider not configured' errors

Ensure the correct environment variable is exported before running kagent install: OPENAI_API_KEY, ANTHROPIC_API_KEY, or GEMINI_API_KEY. You can also update the provider credentials via the kagent dashboard under Settings > Model Config.

The MCP server tools for Kubernetes are missing in Claude Desktop

The built-in MCP tools (kmcp) require kagent v0.7+. Run `kagent version` to check. If upgrading, re-run `kagent install --profile demo` to update the in-cluster components.

Frequently Asked Questions about Kagent

What is Kagent?

Kagent is a Model Context Protocol (MCP) server that cloud native agentic ai | discord: https://bit.ly/kagentdiscord It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Kagent?

Follow the installation instructions on the Kagent GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Kagent?

Kagent works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Kagent free to use?

Yes, Kagent is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Kagent Alternatives — Similar Cloud Services Servers

Looking for alternatives to Kagent? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.

Open WebUI

★ 138.2k

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Anything LLM

★ 60.4k

The all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.

LocalAI

★ 46.4k

LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.

Nacos

★ 33.0k

an easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.

Xiaozhi ESP32

★ 26.7k

本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.

Gateway

★ 11.8k

A blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.

Browse More Cloud Services MCP Servers

Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Cloud ServicesBrowse All Servers

Quick Config Preview

{ "mcpServers": { "kagent": { "command": "npx", "args": ["-y", "kagent"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Kagent?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides