MCP Cyclops

Cyclops MCP is a tool that allows AI agents to securely manage and deploy Kubernetes applications through the Model Context Protocol, providing template validation and application creation/update functions

Developer tools Cloud platform #Kubernetes management #AI agent #Application deployment #Template validation .Go

rating : 2.5 points

downloads : 0

update time : 2025-09-03

Open Site

What is Cyclops MCP?

Cyclops MCP (Model Context Protocol) is an AI agent server designed specifically for Kubernetes. It allows AI assistants (such as Cursor, Claude, etc.) to create, update, and manage your containerized applications through secure, high - level abstractions.

How to use Cyclops MCP?

Simply install the Cyclops MCP server, configure your AI agent connection, and you can start deploying and managing Kubernetes applications through natural language instructions without in - depth knowledge of complex YAML configurations.

Use cases

Suitable for development teams to quickly deploy microservices, automate CI/CD pipelines, manage development environments, and scenarios that require frequent updates and adjustments to containerized applications.

Main Features

Create a new module

Quickly create new Kubernetes application modules by specifying templates and configuration values

Get module information

Retrieve detailed information and current status of an existing module by name

List all modules

View a list of all deployed Cyclops modules in the cluster

Update module configuration

Safely modify the configuration parameters and deployment settings of an existing module

Template schema validation

Automatically verify that configuration values comply with template specifications before creation or update

Template storage management

Manage and query the available application template library

Advantages

Abstract the complexity of Kubernetes, allowing both developers and AI to easily manage container applications

Reduce the risk of configuration errors through high - level resource operations

Provide production - ready application deployment guarantees

Support multiple installation methods, including one - click UI installation and manual deployment

Seamlessly integrate with mainstream AI agent tools (such as Cursor)

Limitations

The Cyclops platform needs to be deployed to the Kubernetes cluster first

Currently mainly supports the deployment of applications in the Cyclops module format

Requires basic access permissions to the Kubernetes cluster

How to Use

Install the Cyclops platform

Ensure that the Cyclops control plane and UI are installed in your Kubernetes cluster

Install the MCP server

One - click install the MCP server through the plugin page of the Cyclops UI

Expose the MCP service

Expose the MCP server to the local machine through port forwarding

Configure the AI agent

Add the MCP server connection to your AI tool configuration

Usage Examples

Quickly deploy a web application

Quickly deploy an Nginx web server through an AI agent

Application configuration update

Dynamically adjust the resource configuration of a running application

Environment inspection

Check the status of all currently deployed applications

Frequently Asked Questions

What prerequisites are required for Cyclops MCP?

Which AI agent tools are supported?

How to ensure the security of deployment?

Does it support custom templates?

Related Resources

Cyclops official documentation

Complete Cyclops platform usage guide and API documentation

GitHub repository

MCP server source code and issue tracking

Kubernetes learning resources

Official Kubernetes documentation

MCP protocol specification

Official specification of the Model Context Protocol

🚀 Cyclops MCP (Model Context Protocol)

Cyclops MCP enables your preferred AI agent to manage your Kubernetes applications. Cyclops MCP servers offer tools for agents to safely create and update existing applications.

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

This implies that it can examine all your existing templates and their schemas to create accurate and production-ready applications. Since your agent creates high-level resources (Cyclops Modules) instead of modifying every line of your Kubernetes resources (Deployments, Services, and Ingresses), there is much less chance of misconfiguration.

It allows you to move quickly and ensures that no undetected misconfigurations reach your production environment.

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

🚀 Quick Start

📦 Installation

Install via UI

The simplest way to install the Cyclops MCP server is through the Cyclops UI. Although instructions for binary and kubectl installation are provided below, the recommended method is via the UI.

⚠️ Important Note

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

Install the Cyclops MCP by navigating to the sidebar “Addon” > "MCP server". Then click "Install Cyclops MCP server", and your Cyclops MCP server will be up and running within seconds.
Now that your MCP server is running, all that remains is to expose it outside your cluster and connect your AI agent to it. To expose the MCP server on localhost, you can simply port-forward it using the following command:
```
kubectl port-forward -n cyclops svc/cyclops-mcp 8000:8000
```
Your server is now accessible at localhost:8000.
To connect it to an AI agent, you only need to provide the Cyclops MCP server in its configuration. For example, to add it to Cursor, you can use the following JSON:
```
{
  "mcpServers": {
    "cyclops-kubernetes": {
      "url": "http://localhost:8000/sse"
    }
  }
}
```

You can now initiate a new conversation with your AI companion. The above is an example of how we used it with Cursor.

Install stdin binary

1. Ensure Cyclops is installed in your Kubernetes cluster

Check our docs on how to 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 using the following command:

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

3. Add server configuration

⚠️ Important Note

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 the Cyclops MCP server via environment variables. Below is an example of adding configuration to specify 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

The following is a list of environment variables used to configure your Cyclops MCP server:

Property	Details
`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 the mcp-cyclops binary, you can install the Cyclops MCP server with SSE as the transport type to your Kubernetes cluster, allowing all your developers to connect to the same server.

Before installation, ensure Cyclops and all its CRDs are installed in your cluster:

Check that Cyclops pods are running:

kubectl get pods -n cyclops

The output should be:

NAME                            READY   STATUS    RESTARTS   AGE
cyclops-ctrl-676b5d9789-ntcls   1/1     Running   0          94s
cyclops-ui-7798655f97-xdg29     1/1     Running   0          94s

Check if CRDs are installed:

kubectl get crds | grep cyclops-ui

The output should be:

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

Install the Cyclops MCP server using the following command:

kubectl apply -f https://raw.githubusercontent.com/cyclops-ui/mcp-cyclops/refs/heads/main/install/mcp-server.yaml

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
```

Add your Cyclops MCP server host, or if you are testing it, the localhost address where you port-forwarded the MCP service:

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

✨ Features

Tools

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