ocm-mcp-server (io.github.sandeepbazar/ocm-mcp-server) MCP Server

The ocm-mcp-server provides “Guardrailed fleet ops for AI agents” using OCM for multi-cluster Kubernetes. The included description specifies policy, approval, and audit, indicating controlled operational workflows across Kubernetes clusters for agent-driven tasks.

🛠️ Key Features

Guardrailed fleet operations for AI agents
Multi-cluster Kubernetes via OCM
Policy, approval, and audit coverage

🚀 Use Cases

Running controlled fleet operations across multiple Kubernetes clusters
Enabling AI agents to perform OCM-based actions with governance steps

⚡ Developer Benefits

Centralized repository and distribution points
Available via PyPI (pip install ocm-mcp-server) and a container image (ghcr.io/ocm-mcp-server/ocm-mcp-server)
Documentation hosted at https://ocm-mcp-server.github.io/

⚠️ Limitations

Project indicates a move: source now lives at https://github.com/ocm-mcp-server/ocm-mcp-server (per the readme excerpt).

Code

https://github.com/ocm-mcp-server/ocm-mcp-server

Docs

https://ocm-mcp-server.github.io/

PyPI

pip install ocm-mcp-server

Container

ghcr.io/ocm-mcp-server/ocm-mcp-server

MCP Registry

io.github.ocm-mcp-server/ocm-mcp-server

Install

Configuration

Environment variables

KUBECONFIGrequired

Path to the kubeconfig with the OCM hub context (and optional spoke contexts).

OCM_MCP_HUB_CONTEXT

Kubeconfig context name of the OCM hub cluster (defaults to the current context).

OCM_MCP_READ_ONLY

Set to 'true' to disable the gated write path entirely (read-only fleet access).

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "ocm-mcp-server": {
      "command": "uvx",
      "args": [
        "ocm-mcp-server"
      ],
      "env": {
        "KUBECONFIG": "<YOUR_KUBECONFIG>",
        "OCM_MCP_HUB_CONTEXT": "<YOUR_OCM_MCP_HUB_CONTEXT>",
        "OCM_MCP_READ_ONLY": "<YOUR_OCM_MCP_READ_ONLY>"
      }
    }
  }
}

io.github.sandeepbazar/ocm-mcp-server