OCM MCP Server

by judexzhu

235 downloads

Not rated

GitHub

Developer Tools

About

A comprehensive Model Control Protocol (MCP) server for Red Hat OpenShift Cluster Manager (OCM) API operations. This server provides 12 intelligent tools for cluster management, account operations, and infrastructure monitoring.

Details

Author: judexzhu
Downloads: 235
Categories: Developer Tools

- 12 tools covering cluster, account, and infrastructure operations
- Automatic HCP / Classic cluster type detection
- Smart machine pool management (node_pools vs machine_pools)
- Dynamic external_id resolution for service logs
- Alert severity breakdown and operator condition summaries
- VPC subnet analysis with public/private breakdown

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below

Plugin Name OCM MCP Server

Command (node, npx, python, etc.)

Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "ocm mcp server": {
            "mcp-ocm": {
                "command": "uv",
                "args": [
                    "sync"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "ocm mcp server": {
            "mcp-ocm": {
                "command": "uv",
                "args": [
                    "sync"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "ocm mcp server": {
            "mcp-ocm": {
                "command": "uv",
                "args": [
                    "sync"
                ]
            }
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "ocm mcp server": {
            "mcp-ocm": {
                "command": "uv",
                "args": [
                    "sync"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "ocm mcp server": {
            "mcp-ocm": {
                "command": "uv",
                "args": [
                    "sync"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "ocm mcp server": {
            "mcp-ocm": {
                "command": "uv",
                "args": [
                    "sync"
                ]
            }
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "ocm mcp server": {
            "mcp-ocm": {
                "command": "uv",
                "args": [
                    "sync"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "ocm mcp server": {
            "mcp-ocm": {
                "command": "uv",
                "args": [
                    "sync"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "ocm mcp server": {
            "mcp-ocm": {
                "command": "uv",
                "args": [
                    "sync"
                ]
            }
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "ocm mcp server": {
            "mcp-ocm": {
                "command": "uv",
                "args": [
                    "sync"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "ocm mcp server": {
            "mcp-ocm": {
                "command": "uv",
                "args": [
                    "sync"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "ocm mcp server": {
            "mcp-ocm": {
                "command": "uv",
                "args": [
                    "sync"
                ]
            }
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "ocm mcp server": {
            "mcp-ocm": {
                "command": "uv",
                "args": [
                    "sync"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "ocm mcp server": {
            "mcp-ocm": {
                "command": "uv",
                "args": [
                    "sync"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "ocm mcp server": {
            "mcp-ocm": {
                "command": "uv",
                "args": [
                    "sync"
                ]
            }
        }
    }
}

From the repository

Install Python 3.9+ and uv, clone the repository, run uv sync, create a .env file with your RH_API_OFFLINE_TOKEN (and optional OCM_BASE_URL), then configure your MCP client to run uv --directory /path/to/mcp-ocm run ocm_mcp_server.py passing the token as an environment variable.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "ocm mcp server": {
            "mcp-ocm": {
                "command": "uv",
                "args": [
                    "sync"
                ]
            }
        }
    }
}

McpServers

{
    "mcp-ocm": {
        "command": "uv",
        "args": [
            "sync"
        ]
    }
}

OCM MCP Server

Features(Keep Adding)

- ocm_get_cluster - Get detailed cluster information with automatic HCP/Classic detection
- ocm_get_cluster_machine_pools - Smart pool management (automatically selects node_pools for HCP, machine_pools for Classic)
- ocm_get_cluster_upgrade_policies - Intelligent upgrade policy management for both cluster types

- ocm_get_cluster_service_logs - Service logs using dynamic external_id resolution
- ocm_get_cluster_alerts - Cluster alerts with severity breakdown
- ocm_get_cluster_operators - Operator status monitoring with condition summaries
- ocm_get_cluster_install_logs - Installation logs and history

- ocm_get_cluster_vpc - VPC information with subnet analysis (public/private breakdown)
- ocm_get_cluster_ingress - Ingress configuration and DNS information
- ocm_get_cluster_identity_providers - Authentication provider configuration

- ocm_get_cluster_limited_support_reasons - Support status and restrictions
- ocm_get_accounts_by_email - Account management and user lookup

Installation

Prerequisites

- Python 3.9+ - uv package manager

Setup

1. Clone and Navigate

   git clone <repository-url>

   cd mcp-ocm

2. Install Dependencies

   uv sync

3. Environment Configuration
Create a .env file with your Red Hat API credentials:

   # Required: Your Red Hat API offline token

   RH_API_OFFLINE_TOKEN=your_offline_token_here

   

   # Optional: OCM API base URL (defaults to https://api.openshift.com)

   OCM_BASE_URL=https://api.openshift.com

Getting your offline token:
1. Visit Red Hat API Tokens
2. Generate or copy your offline token
3. Add it to your .env file

Usage

Running the MCP Server

{
  "mcpServers": {
    "ocm": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/your/mcp-ocm",
        "run",
        "ocm_mcp_server.py"
      ],
      "env": {
        "RH_API_OFFLINE_TOKEN": "your_actual_offline_token_here",
        "OCM_BASE_URL": "https://api.openshift.com"
      }
    }
  }
}

Tools Reference

| Tool | Purpose | Cluster Types | Key Features |
|------|---------|---------------|--------------|
| ocm_get_cluster | Basic cluster info | All | HCP/Classic detection |
| ocm_get_cluster_machine_pools | Pool management | All | Smart endpoint selection |
| ocm_get_cluster_service_logs | Service logs | All | Dynamic external_id resolution |
| ocm_get_cluster_identity_providers | Auth config | All | Provider type analysis |
| ocm_get_cluster_ingress | Ingress config | All | DNS and routing info |
| ocm_get_cluster_limited_support_reasons | Support status | All | Restriction analysis |
| ocm_get_cluster_install_logs | Install history | All | Log size and content |
| ocm_get_cluster_alerts | Alert monitoring | All | Severity breakdown |
| ocm_get_cluster_operators | Operator status | All | Condition summaries |
| ocm_get_cluster_upgrade_policies | Upgrade management | All | Multi-endpoint handling |
| ocm_get_cluster_vpc | Network info | All | Subnet analysis |
| ocm_get_accounts_by_email | Account lookup | N/A | User management |

API Coverage

Cluster Management API

- /api/clusters_mgmt/v1/clusters/{id} - /api/clusters_mgmt/v1/clusters/{id}/machine_pools - /api/clusters_mgmt/v1/clusters/{id}/node_pools - /api/clusters_mgmt/v1/clusters/{id}/upgrade_policies - /api/clusters_mgmt/v1/clusters/{id}/control_plane/upgrade_policies - /api/clusters_mgmt/v1/clusters/{id}/node_pools/{pool_id}/upgrade_policies

Service Logs API

- /api/service_logs/v1/clusters/{external_id}/cluster_logs

Infrastructure APIs

- /api/clusters_mgmt/v1/clusters/{id}/vpc - /api/clusters_mgmt/v1/clusters/{id}/ingresses - /api/clusters_mgmt/v1/clusters/{id}/identity_providers

Monitoring APIs

- /api/clusters_mgmt/v1/clusters/{id}/metric_queries/alerts - /api/clusters_mgmt/v1/clusters/{id}/metric_queries/cluster_operators

Account Management API

- /api/accounts_mgmt/v1/accounts?search=email='...

Dependencies

- httpx: Async HTTP client
- mcp: Model Control Protocol framework
- python-dotenv: Environment variable management
- asyncio: Async/await support

License

This project is licensed under the MIT License.

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Jump to

Setting up with Highlight

From the repository

Claude Desktop / Cursor

McpServers

OCM MCP Server

Features(Keep Adding)

Installation

Prerequisites

Setup

Usage

Running the MCP Server

Tools Reference

API Coverage

Cluster Management API

Service Logs API

Infrastructure APIs

Monitoring APIs

Account Management API

Dependencies

License

Install

More like this

Sentry

Github

Git

GitLab

Context 7

Playwright