Moretes Architect MCP
io.github.fernando-moretes/moretes-aws-architect-mcp · v0.5.0 · score 89/100 · checked 2026-11-22
Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works
Evidence-first architecture workbench: 48 deterministic tools, 10 architect personas, any cloud
Source: https://github.com/fernando-moretes/moretes-aws-architect-mcp
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 48 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (agent_eval_plan). Require confirmation before the agent calls them. |
What was checked
- https://mcp.moretes.com/mcp: answers without auth
- npm: moretes-aws-architect-mcp@0.5.0 (static checks only; code not executed)
Public tools: architect_panel, code_review_architecture, dependency_manifest_review, requirements_check, architecture_pattern, service_compare, decision_record, well_architected_review, threat_model, failure_rehearsal, capacity_plan, cost_model, slo_budget, migration_plan, architecture_diagram, implementation_plan, agent_tool_contract, c4_model, sequence_diagram, service_equivalents, data_classification, openapi_review, event_contract, latency_budget, queue_sizing, dr_strategy, retry_policy, storage_growth, finops_unit_economics, postmortem
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-fernando-moretes-moretes-aws-architect-mcp-4ee697fd)