Helm Chart CLI MCP Server

What does “Helm Chart CLI” MCP Server do?

Helm Chart CLI MCP Server provides a bridge between AI assistants and the Helm package manager for Kubernetes. This MCP server enables AI assistants to interact with Helm using natural language requests, automating common Helm workflows such as installing charts, managing repositories, and executing various Helm commands. By exposing Helm’s capabilities through the Model Context Protocol, it empowers developers and operations teams to query, manage, and control Kubernetes application deployments more efficiently. The server enhances development workflows by allowing tasks like chart creation, chart linting, repository management, and autocompletion of commands to be performed programmatically or through AI-driven interactions.

List of Prompts

No prompt templates were mentioned in the available documentation or codebase.

Ready to grow your business?

Start your free trial today and see results within days.

Request demo Log in

List of Resources

No explicit MCP resources were described in the available documentation or codebase.

List of Tools

• helm_completion
  Generates autocompletion scripts for various shells (bash, fish, powershell, zsh).
• helm_create
  Creates a new Helm chart with a specified name and optional starter template.
• helm_lint
  Runs verification tests on a chart to ensure it is well-formed.

Join our newsletter

Get latest tips, trends, and deals for free.

Email address

Subscribe

Use Cases of this MCP Server

• Automated Chart Creation
  Developers can request new Helm charts to be scaffolded programmatically, streamlining the process of Kubernetes application deployment setup.
• Chart Validation via Linting
  AI assistants can invoke the linting tool to automatically validate chart correctness, reducing manual errors and improving deployment reliability.
• Shell Autocompletion Assistance
  Provides shell-specific autocompletion scripts to streamline command-line use of Helm, improving developer productivity.
• Integration with AI Assistants
  Enables AI-powered agents to manage Helm operations directly, supporting conversational DevOps and reducing context switching.
• Repository and Chart Management
  (Assumed from typical Helm operations, but not explicitly listed in tools—limit to what is documented.)

How to set it up

Windsurf

1. Ensure Python 3.8+ and Helm CLI are installed.
2. Clone the repository:

   git clone https://github.com/modelcontextprotocol/servers.git
   cd src/helm
   

3. Install dependencies and run:

   uv venv
   source .venv/Scripts/Activate.ps1
   uv pip install -e .
   mcp-server-helm
   

4. Add the MCP server to your Windsurf configuration:

   {
     "mcpServers": {
       "helm-chart-cli": {
         "command": "mcp-server-helm",
         "args": []
       }
     }
   }
   

5. Save, restart Windsurf, and verify connection.

Securing API Keys Example

{
  "mcpServers": {
    "helm-chart-cli": {
      "command": "mcp-server-helm",
      "args": [],
      "env": {
        "API_KEY": "${HELM_MCP_API_KEY}"
      },
      "inputs": {
        "api_key": "${HELM_MCP_API_KEY}"
      }
    }
  }
}

Claude

1. Ensure prerequisites: Python 3.8+ and Helm CLI installed.
2. Clone and set up as above.
3. Edit your Claude configuration:

   {
     "mcpServers": {
       "helm-chart-cli": {
         "command": "mcp-server-helm",
         "args": []
       }
     }
   }
   

4. Save and restart Claude. Confirm server registration.

Cursor

1. Install Python 3.8+ and Helm CLI.
2. Clone, install, and launch the MCP server as above.
3. Add to Cursor’s config:

   {
     "mcpServers": {
       "helm-chart-cli": {
         "command": "mcp-server-helm",
         "args": []
       }
     }
   }
   

4. Save and restart Cursor. Test connection.

Cline

1. Ensure prerequisites and clone/setup as above.
2. Add the MCP server to Cline’s configuration:

   {
     "mcpServers": {
       "helm-chart-cli": {
         "command": "mcp-server-helm",
         "args": []
       }
     }
   }
   

3. Save, restart Cline, and verify.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "helm-chart-cli": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “helm-chart-cli” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Based on the above, Helm Chart CLI MCP Server provides solid tool support and clear setup instructions, but lacks explicit resource and prompt lists, as well as documentation on Roots or sampling. The documentation is practical and focused, making it a good fit for technical users.

MCP Score

Rating:
This MCP server implementation is practical and well-documented for tool exposure and setup, but is missing full MCP resource/prompt primitives and advanced features documentation. It would rate a 6/10—solid for practical use, but not as feature-complete as the best examples.