Cortex Resource Manager
Manages Kubernetes deployments, services, and worker nodes, providing tools for MCP server lifecycle management (listing, starting, stopping, scaling), worker node provisioning and destruction, and resource allocation tracking within a Kubernetes cluster.
Integrates with Proxmox for VM provisioning when creating burst workers, enabling automated creation of virtual machines that are joined to the Kubernetes cluster as worker nodes.
Integrates with Talos Linux for VM provisioning when creating burst workers, enabling automated creation of Talos-based virtual machines that are joined to the Kubernetes cluster as worker nodes.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Cortex Resource Managerstart 3 more workers for the data pipeline job"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
cortex-resource-manager [ARCHIVED]
⚠️ This repository has been archived and is no longer maintained.
Migration
This MCP server has been integrated into the main cortex monorepo:
New location: cortex/packages/resource-manager/
What This Was
An MCP (Model Context Protocol) server for managing:
Resource allocation for Cortex jobs
MCP server lifecycle (start/stop/scale)
Kubernetes worker management
Integration with Proxmox for dynamic node provisioning
Using It Now
# Clone the main cortex repo
git clone https://github.com/ry-ops/cortex.git
cd cortex/packages/resource-manager
# Follow the README in that directoryThe resource manager is now part of the Cortex ecosystem and benefits from unified development, testing, and deployment.
Archive Date
December 19, 2025
Reason
Consolidated into cortex monorepo at packages/resource-manager/ for better integration with Cortex core and simplified maintenance.
Please use the main ry-ops/cortex repository going forward.
Related MCP Connectors
The Cortex MCP server provides read-only access to real-time engineering context from the Cortex developer portal, allowing AI coding assistants to answer natural language questions about your organization's catalog (microservices, libraries, domains, teams, infrastructure), scorecards (engineering standards and best practices), initiatives (goals and deadlines), and Engineering Intelligence metrics. It includes tools for querying documentation, tracking personal entities, and accessing AI-assisted insights across the entire Cortex ecosystem.
Provides capabilities that let LLM agents perform a range of infrastructure management tasks.
Massed Compute MCP — GPU inventory, VM lifecycle, billing, SSH keys, and setup recipes.
Hosted MCP server for task-first delegation to remote workstations and workers.
