Case studies

healthKERI · Archimedes · 2025

Secured agents for cloud operations

Built MCP tools for operating AWS, Kubernetes, and GCP from chat with authentication, explicit approval, and audit trails.

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.

The parts I was responsible for.

I built Model Context Protocol tools and the security controls around them, then connected those tools to cloud and cluster APIs.

  • MCP tools for AWS, Kubernetes, and GCP operations.
  • Cryptographic authentication and explicit approval for actions.
  • Audit records for requested and completed operations.
  • Deployment automation, Kubernetes manifests, RBAC, network policy, services, firewall rules, and QR-based TOTP.
01

Separate intent from execution

The agent can prepare an operation, but the operator sees the proposed change and approves it before the tool executes it.

02

Put security at the tool boundary

Authentication, authorization, and audit behavior travel with the operation rather than depending on the surrounding chat interface.

03

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.

What the implementation had to prove.

  • AWS and Kubernetes server deployment flows.
  • Kubernetes RBAC, network policy, service, and manifest operations.
  • GCP firewall operations and QR-based TOTP authentication.

Claim boundary: Archimedes was proprietary. This page describes the approved public product concept and my technical scope, not private source code, customers, or adoption.