Back to Home
maxamillion icon

rhoai-mcp-prototype

Verified Safe

by maxamillion

Overview

Enables AI agents to programmatically interact with Red Hat OpenShift AI (RHOAI) environments, replicating dashboard capabilities for ML lifecycle management.

Installation

Run Command
rhoai-mcp

Environment Variables

  • RHOAI_MCP_AUTH_MODE
  • RHOAI_MCP_KUBECONFIG_PATH
  • RHOAI_MCP_KUBECONFIG_CONTEXT
  • RHOAI_MCP_API_SERVER
  • RHOAI_MCP_API_TOKEN
  • RHOAI_MCP_ENABLE_DANGEROUS_OPERATIONS
  • RHOAI_MCP_READ_ONLY_MODE

Security Notes

The server directly interacts with the Kubernetes API. Its security depends on the permissions of the Kubernetes service account or kubeconfig it uses. It includes safety features like explicit confirmation for 'delete' operations and a 'read-only' mode, which are good practices. No 'eval' or obvious obfuscation detected. Hardcoded secrets are not present; S3 credentials for data connections are passed to tools and stored as Kubernetes secrets. The primary risk is granting the server (and thus, an AI agent interacting with it) excessive permissions to the underlying OpenShift AI cluster.

Similar Servers

Stats

Interest Score0
Security Score8
Cost ClassMedium
Avg Tokens1000
Stars0
Forks0
Last Update2026-01-19

Tags

RHOAIOpenShift AIKubernetesAI AgentsML Platform