Secure agent architecture
MCP servers expose bounded tools. Agents combine a goal, model, memory, policy, and tools into a workflow. Dockprom-AI should begin with read-only diagnostic agents and add mutation only after approval, isolation, audit, and rollback controls have been proven.
Recommended first agents
- Observability Triage Agent: correlates alerts, metrics, logs, and traces.
- AI/LLM Performance Agent: diagnoses Ollama, token, context, queue, and GPU behavior.
- Runbook Recommendation Agent: retrieves cited operational guidance.
- AI Security Detection Agent: identifies injection, leakage, abuse, and anomalous tool activity.
- RAG Quality Agent: monitors retrieval relevance, coverage, and freshness.
- MCP Tool Policy Agent: makes deterministic allow, deny, or approval-required decisions.
- Incident Correlation Agent: produces a draft incident and evidence timeline.
- Remediation Planner Agent: proposes bounded, reversible steps without executing them.
The approval-gated Change Executor Agent should be last. It must never have a general-purpose shell or unrestricted Docker socket.
Harness flow
Untrusted input
-> input classification and injection checks
-> bounded agent goal
-> read-only evidence collection
-> typed plan
-> deterministic OPA policy decision
-> human approval when required
-> narrowly scoped executor
-> independent verification
-> rollback or completion
-> immutable audit event and OpenTelemetry trace
OWASP-aligned controls
- Immutable agent goals and prompt/data separation.
- Unique agent identity and least-privilege tool authorization.
- Strict JSON Schema validation for every tool and inter-agent message.
- Planner, policy, approval, executor, and verifier separation.
- Tenant-isolated memory with provenance, classification, expiry, and quarantine.
- Sandboxed non-root execution with restricted egress and short-lived credentials.
- Signed/pinned agent, skill, MCP, model, and container dependencies.
- Maximum steps, tools, tokens, retries, duration, and delegation depth.
- Kill switches, circuit breakers, canaries, and tested rollback procedures.
- Redacted OpenTelemetry traces and append-only structured audit events.
- Human-facing evidence, uncertainty, blast radius, and rollback before approval.
The complete agent portfolio, secure skill contract, evaluation gates, and
implementation phases are maintained in
docs/AGENT_ROADMAP.md.
Use the OWASP agent, MCP, and RAG controls
as the mandatory design and release checklist.