Helm MCP

Helm MCP runs locally from a Python package published to PyPI: helm-mcp version 0.4.2. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install — the usual command is uvx helm-mcp. It reads these environment variables: KUBECONFIG and HELM_MCP_BINARY; set them in the client's configuration for this server.

Helm MCP runs locally from a container image in an OCI registry such as Docker Hub or GitHub Container Registry: ghcr.io/scgis-wales/helm-mcp:0.4.2. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Docker or another OCI container runtime; started with docker run — the usual command is docker run -i --rm ghcr.io/scgis-wales/helm-mcp:0.4.2.

In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):

{
  "mcpServers": {
    "helm-mcp": {
      "command": "uvx",
      "args": [
        "helm-mcp"
      ],
      "env": {
        "KUBECONFIG": "<value>",
        "HELM_MCP_BINARY": "<value>"
      }
    }
  }
}

Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect