mcpField
O
ocm-mcp

ocm-mcp

Local
github.com/maorfrCloud & Infra8Updated 39w ago

About ocm-mcp

ocm-mcp is an MCP server for connecting AI clients to Red Hat OpenShift Cluster Manager. It can run in a container and supports transports beyond stdio.

Key features

  1. 01Connects to Red Hat OpenShift Cluster Manager
  2. 02Runs with Podman or Docker
  3. 03Supports SSE and other non-stdio transports
  4. 04Authenticates with an OCM token

Use cases

  1. 01Connect Cluster Manager to an MCP client
  2. 02Deploy the MCP server in a container

MCP support

The server connects MCP clients to Red Hat OpenShift Cluster Manager. It supports stdio or non-stdio transports such as SSE.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"ocm": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"ACCESS_TOKEN_URL",
"-e",
"OCM_CLIENT_ID",
"-e",
"OCM_OFFLINE_TOKEN",
"quay.io/maorfr/ocm-mcp"
],
"env": {
"ACCESS_TOKEN_URL": "<ACCESS_TOKEN_URL>",
"OCM_CLIENT_ID": "<OCM_CLIENT_ID>",
"OCM_OFFLINE_TOKEN": "<OCM_OFFLINE_TOKEN>"
}
}
}
}
Run commanddocker run -i --rm -e ACCESS_TOKEN_URL -e OCM_CLIENT_ID -e OCM_OFFLINE_TOKEN quay.io/maorfr/ocm-mcp
Environment variables to set
ACCESS_TOKEN_URLSecret
OCM_CLIENT_ID
OCM_OFFLINE_TOKENSecret

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
ociquay.io/maorfr/ocm-mcp

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

ocm-mcp

MCP server for Red Hat OpenShift Cluster Manager

Running with Podman or Docker

You can run the ocm-mcp server in a container using Podman or Docker. Make sure you have a valid OCM token, which you can obtain by logging into https://console.redhat.com/openshift/token:

Example configuration for running with Podman:

{
  "mcpServers": {
    "ocm-mcp": {
      "command": "podman",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e", "ACCESS_TOKEN_URL",
        "-e", "OCM_CLIENT_ID",
        "-e", "OCM_OFFLINE_TOKEN",
        "-e", "MCP_TRANSPORT",
        "quay.io/redhat-ai-tools/ocm-mcp"
      ],
      "env": {
        "ACCESS_TOKEN_URL": "https://sso.redhat.com/auth/realms/redhat-external/protocol/openid-connect/token",
        "OCM_CLIENT_ID": "cloud-services",
        "OCM_OFFLINE_TOKEN": "REDACTED",
        "MCP_TRANSPORT": "stdio"
      }
    }
  }
}

Running with non-stdio transport

To run the server with a non-stdio transport (such as SSE), set the MCP_TRANSPORT environment variable to a value other than stdio (e.g., sse).

Example configuration to connect to a non-stdio MCP server:

{
  "mcpServers": {
    "ocm-mcp": {
      "url": "https://ocm-mcp.example.com/sse",
      "headers": {
        "X-OCM-Offline-Token": "REDACTED"
      }
    }
  }
}

Replace REDACTED with the value from https://console.redhat.com/openshift/token.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.