Cyclops MCP(模型上下文协议)

by cyclops-ui

Cyclops MCP(模型上下文协议)允许 AI 代理通过创建和更新 Cyclops 模块(Modules)来安全管理 Kubernetes 应用程序。配置可以通过环境变量(如 KUBECONFIG)进行,以指定外部 kubeconfig 文件。

Developer toolsstdioCommunity

Repository-wide counts · Cached 2026-03-07

Overview

The Cyclops MCP(模型上下文协议) MCP server is a publicly available project. Review the upstream repository for installation instructions, supported tools, compatibility, permissions, and current maintenance status.

Configuration

Configuration, transport, authentication, and runtime requirements vary by project. Open the repository before connecting and use the smallest set of credentials and permissions required.

Open the Cyclops MCP(模型上下文协议) repository to read the latest documentation.

KEEP EXPLORING

Compare source, connection, and authentication details before choosing an implementation.

View the complete category

模型上下文协议服务器

modelcontextprotocol

Community

一组用于模型上下文协议(MCP)的参考实现,展示了对大型语言模型(LLM)工具和数据源的安全且受控的访问方式。

Context7 Platform - Up-to-date Code Docs For Any Prompt

upstash

Community

Context7 MCP server providing up-to-date, version-specific documentation and code examples for libraries, enabling coding agents to fetch accurate docs and code snippets. Requires an API key for higher rate limits, passed via CONTEXT7_API_KEY header.

Playwright MCP

Microsoft Corporation

Community

A Model Context Protocol (MCP) server that provides browser automation capabilities using Playwright. Enables LLMs to interact with web pages through structured accessibility snapshots, bypassing the need for screenshots or visually-tuned models.

AIHawk

feder-cr

Community

AIHawk is an anti detect browser and web browsing agent, open source, with an MCP server for coding agents: undetected, no captchas, no blocks. It requires an OpenRouter API key for the standalone web UI mode, which can be provided via the --openrouter-key flag or the OPENROUTER_API_KEY environment variable or a .env file in the running directory.

FROM THE SOURCE

Repository README

Build-time snapshot · Retrieved 2026-10-05

View original

Cyclops MCP (Model Context Protocol)

Cyclops MCP allows your favorite AI agent to manage your Kubernetes applications. Cyclops MCP servers provide tools for agents to create and update existing applications safely.

https://github.com/user-attachments/assets/0c675c33-1e36-4fdb-bf8c-2fd7fb491e6b

This means it can check all of your existing templates and the schema of those templates to create accurate and production-ready applications. Your agent now has much less room to make a misconfiguration since it creates high-level resources (Cyclops Modules) instead of touching every line of your Kubernetes resources (Deployments, Services, and Ingresses).

It allows you to move fast and ensure no uncaught misconfigurations are hitting your production.

With Cyclops and our MCP, you can now abstract Kubernetes complexity from your developers AND your AI agents

Install via UI

The easiest way to install the Cyclops MCP server is through the Cyclops UI. Below are instructions on how to install it via binary and kubectl, but the recommended way of installing it is via the UI.

⚠️ To install Cyclops MCP through the UI, you should run Cyclops on a version v0.20.1 or greater

  1. Install the Cyclops MCP by going to sidebar “Addon” > "MCP server". You can now click "Install Cyclops MCP server" and your Cyclops MCP server will be up and running in a few seconds.
addon-install
  1. Now that your MCP server is up running, all thats left is exposing it outside of your cluster and connecting your AI agent to it.

    To expose the MCP server on localhost you can simply port-forward it with the following command:

    kubectl port-forward -n cyclops svc/cyclops-mcp 8000:8000
    

    Your server is now available on localhost:8000.

  2. To connect it to an AI agent you will just have to provide the Cyclops MCP server in its configuration. For example, to add it to Cursor, you can simply add it with the following JSON:

    {
      "mcpServers": {
        "cyclops-kubernetes": {
          "url": "http://localhost:8000/sse"
        }
      }
    }
    

You can now start a fresh conversation with your AI companion. Above is an example of how we used it with Cursor.

Install stdin binary

1. Make sure Cyclops is installed in your Kubernetes cluster

Check our docs on how it install it with a single command - https://cyclops-ui.com/docs/installation/install/manifest

2. Download MCP server

You can download the Cyclops MCP server binary with the following command:

GOBIN="$HOME/go/bin" go install github.com/cyclops-ui/mcp-cyclops/cmd/mcp-cyclops@latest

3. Add server configuration

⚠️ By default, Cyclops MCP will use the .kube/config file to connect to your cluster

Configure your MCP Cyclops server:

{
  "mcpServers": {
    "mcp-cyclops": {
      "command": "mcp-cyclops"
    }
  }
}

Configuration

You can configure Cyclops MCP server via env variables. Below is an example of adding the configuration for specifying the kubeconfig file the Cyclops MCP server should use when managing your Cyclops applications.

{
  "mcpServers": {
    "mcp-cyclops": {
      "command": "mcp-cyclops",
      "env": {
        "KUBECONFIG": "/path/to/your/kubeconfig"
      }
    }
  }
}

Environment variables

Below is the list of environment variables used for configuring your Cyclops MCP server:

Env var Description
KUBECONFIG Path to kubeconfig file (optional, defaults to in-cluster config or $HOME/.kube/config)
CYCLOPS_KUBE_CONTEXT Kubernetes context to use (optional)
CYCLOPS_MODULE_NAMESPACE Namespace where modules are stored
CYCLOPS_HELM_RELEASE_NAMESPACE Namespace for Helm releases
CYCLOPS_MODULE_TARGET_NAMESPACE Target namespace for modules

Install to a Kubernetes cluster manually

Instead of having each developer install mcp-cyclops binary, you can install the Cyclops MCP server with SSE as transport type to your Kubernetes cluster and allow all of your developers to connect to the same server.

  1. Before installing, make sure Cyclops and all its CRDs are installed in your cluster:

    1. Check Cyclops pods are running:

      kubectl get pods -n cyclops
      

      Should write:

      NAME                            READY   STATUS    RESTARTS   AGE
      cyclops-ctrl-676b5d9789-ntcls   1/1     Running   0          94s
      cyclops-ui-7798655f97-xdg29     1/1     Running   0          94s
      
    2. Check if CRDs are installed

      kubectl get crds | grep cyclops-ui
      

      Should write:

      modules.cyclops-ui.com             2025-04-26T15:28:18Z
      templateauthrules.cyclops-ui.com   2025-04-26T15:28:18Z
      templatestores.cyclops-ui.com      2025-04-26T15:28:18Z
      
  2. Install Cyclops MCP server with the following command:

    kubectl apply -f https://raw.githubusercontent.com/cyclops-ui/mcp-cyclops/refs/heads/main/install/mcp-server.yaml
    
  3. You can now expose the cyclops-mcp service. To test your MCP server, you can port-forward it:

    kubectl port-forward svc/cyclops-mcp -n cyclops 8000:8000
    
  4. Add your Cyclops MCP server host, or in case you are testing it, the localhost address where you port-forwarded the MCP service:

    {
      "mcpServers": {
        "mcp-cyclops": {
          "url": "http://localhost:8000/sse"
        }
      }
    }
    

Tools

Tool Description
create_module Create new Module. Before calling this tool, make sure to call get_template_schema to validate values for the given template
get_module Fetch Module by name
list_modules List all Cyclops Modules
update_module Update Module by Name. Before calling this tool, make sure to call get_template_schema to validate values for the given template
get_template_schema Returns JSON schema for the given template. Needs to be checked before calling create_module tool
get_template_store Fetch Template Store by Name
list_template_store List Template Stores from cluster