An agent action still needs a human decision.
Cloud automation is useful only when an operator can understand and control what an agent is about to change. The tool boundary needed to combine conversational workflows with the checks expected from infrastructure software.
What I owned
I built Model Context Protocol tools that connected the product to AWS, Kubernetes, and GCP APIs.
- AWS server-deployment tooling.
- GCP firewall tools with validation for port rules, priorities, and network tags.
- Kubernetes deployment manifests and tooling for RBAC, network policies, and services.
Key decisions
Generate explicit infrastructure configuration
Deployment tools produce concrete manifests and API requests that an operator can inspect before the infrastructure changes.
Validate cloud API constraints
Firewall rules validate ports, priorities, and network tags before sending changes to GCP.
Return concrete infrastructure state
Tools report the resources they inspected or changed so the operator can verify the result instead of relying on an assistant summary.
How I tested it
- AWS and Kubernetes server deployment flows.
- Kubernetes RBAC, network policy, service, and manifest operations.
- GCP firewall rule validation and operations.
Built with: MCP, AWS, Kubernetes, GCP, Python
A note on scope
Archimedes was proprietary. This page describes the approved public product concept and my technical scope, not private source code, customers, or adoption.