An MCP server for evidence-driven cloud architecture that gives code agents 48 deterministic tools and 10 architect personas without server model calls or API keys.
Convene architect personas for solution, enterprise, business, data, infrastructure, software, AI, security, governance, and FinOps, returning questions, checks, deliverables, and tool recommendations.
Turn requirements into explicit gaps, compare architecture patterns and AWS services, generate ADRs, Well-Architected reviews, threat models, migration plans, implementation plans, and agent tool contracts.
Create and validate C4, sequence, and architecture diagrams in Mermaid; map cloud services across AWS, Azure, GCP, OCI, and open source; classify data and design event contracts.
Review code, dependency manifests, OpenAPI docs, IAM policies, CloudFormation templates, Terraform/OpenTofu plans, Kubernetes manifests, MCP server safety, and MCP client configs.
Calculate capacity, latency budgets, queue sizing, DR tiers, retry policies, storage growth, SLO error budgets, costs, and FinOps unit economics.
Generate blameless postmortems and operational runbooks; design failure drills and AI agent evaluation plans.
Search live AWS documentation and check regions/availability via the official AWS Knowledge MCP; find/configure official AWS MCP integrations and read public GitHub repository metadata.
Run offline via CLI or as a stdio/HTTP MCP server; local mode adds optional read-only AWS account tools.
Provides tools for retrieving public GitHub metadata, letting the model look up public repository information as part of architecture research and integration discovery.
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., "@Moretes AWS Architect MCP Help me design an order API: compare Lambda vs ECS, ask about traffic, data, SLO, budget"
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.
Um servidor MCP que coloca 48 ferramentas determinísticas de arquitetura e 10 personas de arquiteto dentro do seu agente de código. O modelo do seu cliente raciocina; o servidor devolve cálculos, estruturas, fontes oficiais e lacunas explícitas. O servidor nunca chama um modelo, nunca acessa a sua conta pela internet e não precisa de chave de API.
Feito por Fernando Azevedo, Arquiteto de Tecnologia da Informação Especialista e AWS Community Builder (AI Engineering). É o que eu uso para decidir arquitetura no dia a dia, aberto para a comunidade usar, auditar e estender.
Pede uma API, ele pergunta antes de sugerir. O agente chama requirements_check e depois architect_panel; nenhum número é inventado.
Calcula, não chuta. No Kiro, latency_budget soma os passos em série, pega o maior dos paralelos e mostra onde o tempo vai.
Trava o apply perigoso no pipeline. O mesmo motor roda offline como CLI, com Markdown, JSON ou SARIF e exit code por severidade.
Os GIFs são trechos dos vídeos do curso gratuito, narrados na minha voz, com as chamadas e as respostas reais do servidor. Os JSON completos estão em docs/examples.
Related MCP server: Cloud Architect
Sem chave, sem cadastro:
# Claude Code
claude mcp add --transport http moretes-architect https://mcp.moretes.com/mcp
# Codex
codex mcp add moretes-architect --url https://mcp.moretes.com/mcp
# Gemini CLI
gemini mcp add --transport http moretes-architect https://mcp.moretes.com/mcpKiro (.kiro/settings/mcp.json), Cursor (.cursor/mcp.json) e Amazon Q (mcp.json):
{
"mcpServers": {
"moretes-architect": {
"url": "https://mcp.moretes.com/mcp",
"autoApprove": []
}
}
}VS Code (.vscode/mcp.json):
{
"servers": {
"moretes-architect": { "type": "http", "url": "https://mcp.moretes.com/mcp" }
}
}Claude Desktop e qualquer cliente stdio, depois de rodar local:
{ "mcpServers": { "moretes-architect": { "command": "node", "args": ["/CAMINHO/ABSOLUTO/dist/stdio.js"] } } }Passo a passo de cada cliente, verificação e erros comuns: docs/clients.md.
Cota pública: 300 requisições por dia por cliente e 3.000 no total; acima disso, 429. O mesmo servidor responde em https://fernando.moretes.com/api/mcp, mas esse endereço passa pelo site e todos os seus usuários dividem uma única cota diária; use a URL direta para ter a sua. Para volume ou entradas privadas, rode local.
Depois de conectar, peça ao agente:
"Use o Moretes Architect. Preciso de uma API de pedidos para um marketplace, 300 pedidos por minuto no pico. Pergunte o que falta antes de sugerir, convoque os arquitetos de solução, segurança e FinOps, compare Lambda e ECS, desenhe o C4 e registre a decisão em um ADR."
Grupo | Ferramentas | Para quê |
Personas e código |
| Convocar arquitetos de solução, enterprise, negócio, dados, infraestrutura, software, IA, segurança, governança e FinOps; revisar código e manifestos de dependência |
Arquitetura e decisões |
| Do requisito ao ADR, com os seis pilares, STRIDE, capacidade, custo datado e SLO |
Design: diagramas, dados, contratos |
| C4 e sequência em Mermaid validados; equivalência AWS, Azure, GCP, OCI e open source em 43 capacidades; LGPD, GDPR e PCI como ponteiros; OpenAPI; contrato CloudEvents |
Confiabilidade, operação e FinOps |
| Orçamento de latência, Erlang C, tier de DR por RTO/RPO, backoff com jitter, crescimento de armazenamento, custo por unidade, postmortem e runbook |
Agentes de IA e segurança de MCP |
| Plano de avaliação, controles contra injeção, RAG com autorização antes do top-k, revisão de outros servidores MCP e da configuração do seu cliente |
Revisão de IaC |
| Plano Terraform/OpenTofu em JSON, CloudFormation, manifestos Kubernetes, políticas IAM |
AWS Knowledge ao vivo |
| Documentação oficial atual, regiões e disponibilidade, pelo MCP oficial da AWS |
Integrações oficiais e GitHub |
| Catálogo dos 61 servidores oficiais awslabs com versão fixada; metadados públicos de repositórios |
iam_policy_review lê política IAM da AWS, role definition do Azure e bindings do Google Cloud (provider). Toda ferramenta de cálculo e revisão publica outputSchema, e o cliente valida a saída.
Mais 20 prompts (10 fluxos e um architect_<papel> por persona), 18 resources (moretes://guide, moretes://boundaries, moretes://tools, moretes://personas/<id>, moretes://skills/<id>) e, só no modo local, 5 ferramentas opcionais de conta AWS e federação com os servidores oficiais.
Guia de cada ferramenta: docs/tools-guide.md · Schemas: docs/tools.md · Saídas reais: docs/examples · Personas: docs/personas.md
Na versão 0.5.0, node dist/cli.js manifest exporta os contratos públicos completos com hashes por ferramenta, incluindo schemas de saída e anotações de segurança. Como verificar e comparar contratos. A instalação local e o endpoint HTTP permitem comparar os mesmos contratos; confira a versão em uso antes de comparar.
c4_modelEntrada: pessoas, sistemas e relações explícitas. Saída: Mermaid validado (id duplicado, aresta solta e rótulo com sintaxe perigosa são recusados). O GitHub renderiza abaixo exatamente o que a ferramenta devolveu em docs/examples/c4_model.json:
flowchart TB
buyer(["Buyer<br/>Places and tracks orders"])
subgraph system_Orders_platform["Orders platform"]
web["Storefront [Next.js]"]
api["Orders API [Node.js on Fargate]"]
db["Orders DB [PostgreSQL]"]
bus["Order events [EventBridge]"]
end
psp[["Payment provider [REST + webhooks]"]]
buyer -->|"uses"| web
web -->|"calls (HTTPS/JSON)"| api
api -->|"reads and writes"| db
api -->|"authorizes payment"| psp
psp -->|"webhook: payment captured"| api
api -->|"publishes OrderPlaced"| bus
classDef person fill:#1f3b63,stroke:#5b9bd5,color:#fff
class buyer person
classDef external fill:#4a4a4a,stroke:#9a9a9a,color:#fff
class psp externalmcp_server_review recebe o tools/list de outro servidor e procura texto de instrução escondido na descrição, parâmetros perigosos, anotação mentirosa e nomes duplicados. Contra o servidor de exemplo em docs/examples/mcp_server_review.json:
{
"summary": { "high": 5, "medium": 1, "info": 0 },
"verdict": "Do not auto-approve; review each high finding with the server author or pin to an allowlist",
"findings": [
{ "severity": "high", "target": "read_file", "message": "Description contains instruction-like text (references local secret files); tool-poisoning indicator." },
{ "severity": "high", "target": "read_file", "message": "Parameters that typically carry commands, raw queries, URLs or paths: path. Require an allowlist and per-call approval." }
]
}Os servidores MCP de nuvem são operacionais: executam na conta. Faltava a parte de antes: levantar requisitos, comparar com honestidade entre provedores, calcular em vez de chutar, revisar com evidências e registrar a decisão. Este projeto faz essa parte, no mesmo lugar onde o código nasce, sem custo de inferência no servidor e sem receber credenciais.
Três regras atravessam todas as ferramentas:
Pergunta antes de assumir. Requisito que falta volta como pergunta, não como valor típico.
Calcula com entrada auditável. Preço só com fonte e data; fórmula explícita na saída.
Heurística é triagem. Controle marcado como atendido sem evidência volta como desconhecido; toda revisão diz o que não cobre.
git clone https://github.com/fernando-moretes/moretes-aws-architect-mcp.git
cd moretes-aws-architect-mcp && npm ci --ignore-scripts && npm run build
terraform show -json tfplan > plan.json
node dist/cli.js call terraform_plan_review --input plan.json --format sarif --fail-on high > review.sarif
# exit 0: ok · 1: achados no nível --fail-on ou acima · 2: erro de uso ou entradaRoda offline e sem cota. O SARIF entra no code scanning do GitHub; o Markdown vai para o resumo do job. GitHub Actions, GitLab CI e pre-commit prontos em docs/pipelines.md.
Onde | Como |
Claude Code (plugin + skill) |
|
Gemini CLI |
|
Qualquer agente com Agent Skills |
|
GitHub Actions |
|
pre-commit | hooks |
Docker |
|
Detalhes e exemplos: docs/integrations-clients.md.
npm ci --ignore-scripts && npm run build
npm start # MCP stdio (o protocolo usa o stdout; não é um chat)
npm run http # http://127.0.0.1:8787/mcp e a landing local
node dist/cli.js listAs ferramentas de conta AWS (identidade STS, recursos por tag, histórico de custo) e a federação com os servidores oficiais são opt-in por variável de ambiente e só existem no stdio: o HTTP público nunca as expõe. Detalhes em docs/clients.md e docs/integrations.md. O pacote está publicado no npm. Use npx --yes --package moretes-aws-architect-mcp@0.5.0 moretes-architect list para o CLI ou npx --yes --package moretes-aws-architect-mcp@0.5.0 moretes-aws-architect-mcp para stdio.
Em fernando.moretes.com/mcp: conexão por cliente, um playground que chama o servidor de verdade, as ferramentas por grupo, as personas, troubleshooting e FAQ. O curso tem dez aulas, cada uma com vídeo, áudio e texto, quizzes e certificado:
# | Aula |
01 | O que é MCP e o que é o Moretes Architect |
02 | Conectar em 30 segundos: Claude Code, Codex, Kiro, Cursor e VS Code |
03 | Da ideia à decisão: requisitos, painel de arquitetos e ADR |
04 | Desenhar e contratar: C4, sequência, eventos e OpenAPI |
05 | Números que defendem a decisão: capacidade, latência, filas e custo |
06 | Revisar com evidências: Well-Architected, ameaças, dados e IAM |
07 | IaC e código no pipeline: Terraform, CloudFormation, Kubernetes e o CLI |
08 | Operar e recuperar: DR, retries, ensaio de falha, runbook e postmortem |
09 | Agentes de IA em produção e segurança de MCP |
10 | Personas, fontes oficiais, modo local e como contribuir |
O servidor público processa a entrada em memória e registra só id da requisição, status e duração. Nunca argumentos, prompts ou resultados.
Só duas famílias saem para a internet: aws_knowledge_* (a consulta vai para o MCP oficial da AWS) e github_public_repository (api.github.com). Todo o resto é cálculo local.
Contadores mensais em /stats.json registram apenas nomes de ferramentas, sem argumentos, resultados ou identidade; não representam usuários únicos ou análises bem-sucedidas.
A cota por cliente usa sha256(dia + IP) com validade de dois dias; o IP bruto não é guardado.
Não envie segredos, dados de clientes ou arquitetura confidencial ao endpoint público; para isso existe o modo local.
Sem SLA. Serviço comunitário, mantido por uma pessoa, com orçamento alvo de US$ 30 por mês.
Tudo em PRIVACY.md e SECURITY.md.
flowchart LR
C[Claude Code / Codex / Kiro / Cursor / VS Code] -->|Streamable HTTP| G[API Gateway: 5 rps, rajada 20]
G --> L[Lambda arm64: 48 ferramentas públicas]
L --> Q[DynamoDB: cota global e por cliente]
L --> K[AWS Knowledge MCP oficial]
L --> H[GitHub: metadados públicos]
C -->|stdio, opcional| S[MCP local]
S --> A[Credenciais do SDK + guarda de conta]
A --> R[3 ferramentas de conta, somente leitura]
A --> F[Servidores oficiais instalados + allowlist exata]
P[CLI moretes-architect] --> T[Mesmas ferramentas, offline]A role da Lambda escreve e lê contadores somente na própria tabela DynamoDB e escreve nos próprios logs. Deploy por change set CloudFormation revisado. Design · Custos · Runbook · Evidências do deploy
npm run typecheck && npm test && npm run build && npm audit --omit=dev
npm run smoke -- https://mcp.moretes.com/mcp # consulta pública real
node scripts/examples.mjs # regenera docs/examples com as saídas reais41 testes offline, 99% das linhas cobertas, cobrem protocolo, cálculos, revisões, isolamento entre público e local, limites de entrada e federação. CI em Node 22 e 24, CodeQL, Dependabot e SBOM CycloneDX a cada release. Cada saída documentada em docs/examples é um teste: se uma ferramenta mudar de comportamento, o CI acusa. docs/tools.lock.json guarda o hash do nome, da descrição e do schema de cada ferramenta, então qualquer mudança no que o modelo do cliente lê aparece no diff.
Issues e PRs em português ou inglês. Use os templates: bug ou proposta de ferramenta (problema, entrada, saída esperada, limite). Uma ferramenta nova precisa de schema estrito, fronteira de dados externos explícita, limitações na saída e teste. Se você é AWS Community Builder, organiza User Group ou dá aula: o curso e os vídeos são livres para usar em sala.
Clientes · Ferramentas · Personas · Pipelines · FAQ · Troubleshooting · Glossário · Novidades · Workshop · Contribuir · Conduta · Roadmap · Changelog · Atribuições
Projeto independente. Não é um produto da AWS, nem revisão Well-Architected oficial, nem certificação de segurança, nem cotação de preço. AWS e outros nomes pertencem aos seus donos.
Design an evaluation plan for an AI agent: golden set sizing, metrics, judge rubric, red-team cases and regression cadence from explicit capabilities and risks.
Inputs: agent (required), risks (required), capabilities (required), tools, +1 more. Returns: kind, agent, metrics, redTeam, +8 more
Design a per-operation authorization and recovery contract for an agent tool.
Inputs: operation (required), reversible (required), resourceScope (required), approvalRequired (required), +1 more. Returns: kind, sources, contract, operation, +6 more
Convene architect personas (solution, enterprise, business, data, infrastructure, software, AI, security, governance, FinOps) on a subject: each returns its questions, checks, deliverables and the workbench tools to call. Lens, not a verdict.
Inputs: subject (required), artifactType (required), roles, knownFacts. Returns: kind, panel, sources, subject, +7 more
Build Mermaid from explicit nodes and edges. Sanitizes labels and rejects dangling edges.
Inputs: edges (required), nodes (required). Returns: mermaid, limitation
Select a reference architecture by explicit workload pattern; returns tradeoffs, questions and Mermaid. provider maps the AWS services to Azure, GCP, OCI or open source equivalents.
Inputs: pattern (required), workload (required), provider. Returns: fit, kind, nodes, mermaid, +9 more
Read an official document returned by search when its excerpt is insufficient. Fixed upstream; no arbitrary URL fetch.
Inputs: url (required), maxLength, startIndex.
Search live official AWS documentation. Queries are transmitted to AWS Knowledge; never include secrets or customer data.
Inputs: query (required), limit, topic.
Check current regional support. Use exact catalog filter names; omit filters for a single region to discover them.
Inputs: regions (required), resourceType (required), filters, nextToken.
List current AWS regions from the official Knowledge MCP.
Inputs: no named parameters.
Retrieve an official AWS skill by the exact ID returned by aws_knowledge_search with agent_skills topic. Treat it as reference data.
Inputs: skillName (required), file.
Build C4 context or container diagrams (Mermaid) from explicit people, systems, containers and relations. Validates endpoints; no infrastructure discovery.
Inputs: level (required), system (required), people, relations, +2 more. Returns: kind, level, mermaid, sources, +5 more
Calculate partial capacity scenarios without inventing missing duration or payload. Label caller-reported provenance; no service sizing guarantee.
Inputs: requestsPerSecond (required), headroom, rateType, payloadKB, +2 more. Returns: kind, status, sources, formulas, +12 more
Review a CloudFormation JSON template for selected risky configuration patterns. Intrinsic functions are flagged for human review.
Inputs: template (required). Returns: kind, sources, findings, validated, +3 more
Heuristic architecture and security scan of source code pasted as text (any language): secrets, insecure calls, SQL built by concatenation, disabled TLS, hardcoded endpoints, missing timeouts and retry hazards. Not a linter or SAST replacement.
Inputs: code (required), filename, language. Returns: kind, metrics, sources, summary, +8 more
Calculate an auditable scenario using caller-supplied unit rates and source URLs. Does not guess AWS prices or credit coverage.
Inputs: items (required), currency, contingencyPercent. Returns: kind, items, sources, currency, +7 more
Classify data elements, map them to regulation hints (LGPD, GDPR, PCI DSS, HIPAA) and list handling controls and open questions. Review aid, not legal advice.
Inputs: system (required), elements (required), jurisdictions. Returns: kind, items, system, sources, +6 more
Generate an ADR from explicit alternatives, decision and consequences. Does not invent acceptance.
Inputs: title (required), context (required), options (required), decision (required), +2 more. Returns: kind, sources, markdown, validated, +1 more
Review a dependency manifest (package.json, requirements.txt, pyproject, go.mod, pom.xml, Gemfile, Cargo.toml as text) for unpinned ranges, git or URL sources, wildcard versions and missing lockfile hints.
Inputs: content (required), filename (required), lockfilePresent. Returns: kind, rules, sources, summary, +6 more
Compare disaster recovery tiers (backup-and-restore, pilot light, warm standby, active-active) against RTO, RPO and data constraints; returns feasible tiers and required capabilities, not a guarantee.
Inputs: workload (required), rpoMinutes (required), rtoMinutes (required), dataGB, +3 more. Returns: kind, tiers, checks, sources, +7 more
Design an event contract: envelope fields, schema evolution rules, idempotency, ordering, DLQ and replay decisions for a named business event. Deterministic template with open questions.
Inputs: producer (required), consumers (required), eventName (required), payloadFields (required), +2 more. Returns: kind, rules, sources, envelope, +7 more
Design a controlled failure drill with observable success criteria and stop conditions; never executes it.
Inputs: target (required), failure (required), operation (required). Returns: kind, steps, target, failure, +6 more
Compute cost per unit (request, customer, transaction), fixed versus variable split and the volume at which the marginal cost crosses a target. Caller supplies costs; no provider prices are guessed.
Inputs: units (required), period (required), currency, fixedCosts, +2 more. Returns: kind, period, totals, perUnit, +8 more
Read public GitHub repository metadata and contribution links. Fixed api.github.com destination, no tokens, no private repositories.
Inputs: repo (required), owner (required).
Inspect an IAM document for broad grants: AWS policy JSON (default), Azure custom role definition or Google Cloud IAM policy bindings (provider). Heuristic only; the provider analyzers are authoritative.
Inputs: policy (required), provider. Returns: kind, sources, findings, provider, +3 more
Turn an architecture decision into a delivery checklist with validation gates.
Inputs: decision (required), deliverables (required). Returns: kind, stages, sources, decision, +3 more
Search the snapshot of the complete official AWS MCP catalog. Discovery entries are not hosted/executed tools.
Inputs: limit, query. Returns: total, source, servers, boundary, +1 more
Generate a version-pinned local configuration for an official AWS server, or a remote Knowledge config. Does not install, start or approve tools.
Inputs: serverId (required), region, awsProfile. Returns: next, python, source, status, +2 more
Review Kubernetes manifests (parsed JSON objects) for probes, resources, security context, image pinning, host access, secrets in env, PDB and NetworkPolicy coverage. No cluster access.
Inputs: manifests (required). Returns: kind, kinds, objects, sources, +5 more
Split an end-to-end latency objective across hops and show which hops exceed their share. Pure arithmetic over caller-supplied estimates.
Inputs: hops (required), targetMs (required), percentile. Returns: hops, kind, sources, targetMs, +10 more
Review an MCP client configuration JSON (mcpServers map) for unpinned packages, inline secrets, plain HTTP, auto-approved tools and unreviewed enablement.
Inputs: config (required). Returns: kind, rules, servers, sources, +5 more
Heuristic safety review of ANOTHER MCP server from its tools/list output: tool-poisoning text, missing annotations, risky parameters, free-form schemas, name shadowing and context cost. Paste the JSON your client shows.
Inputs: tools (required), serverName (required). Returns: kind, tools, server, sources, +8 more
Prepare phased discovery, pilot, migration and rollback gates; includes AWS Transform integration discovery.
Inputs: source (required), target (required), strategy (required), constraints. Returns: kind, phases, source, target, +7 more
Heuristic review of an OpenAPI 3.x document (JSON): security, pagination, error responses, idempotency, versioning and documentation gaps. Not a linter replacement.
Inputs: document (required). Returns: kind, paths, openapi, sources, +7 more
Generate a blameless postmortem document from incident facts: timeline, impact, detection, contributing factors and owned action items. Rejects action items without owner and due date.
Inputs: title (required), impact (required), severity (required), timeline (required), +7 more. Returns: kind, metrics, coverage, markdown, +1 more
Enumerate injection paths and controls for an agent from its tools and untrusted data sources; produces a checklist with status to fill, not a scan.
Inputs: agent (required), tools (required), humanInLoop (required), untrustedSources (required). Returns: kind, agent, paths, sources, +4 more
Size consumers with Little's law and stable Erlang C: utilization, wait probability, backlog drain time and target consumers. At most 100,000 total concurrent slots (consumers × concurrency).
Inputs: consumers (required), serviceTimeMs (required), arrivalsPerSecond (required), backlogMessages, +2 more. Returns: kind, inputs, stable, sources, +13 more
Plan a retrieval-augmented generation pipeline from corpus facts: chunking, embedding, indexing, authorization, evaluation and cost drivers, with open questions. No vendor is chosen for you.
Inputs: corpus (required), useCase (required), authorization (required), latencyBudgetMs, +1 more. Returns: kind, sizing, stages, sources, +6 more
Turn a workload brief into explicit requirements, gaps and research questions. No inferred SLA or budget.
Inputs: workload (required), constraints, requirements. Returns: kind, sources, workload, nextTools, +5 more
Compute an exponential backoff schedule with jitter, the worst-case wait and whether it fits a deadline; adds idempotency and circuit-breaker guidance.
Inputs: operationIdempotent (required), capMs, factor, jitter, +3 more. Returns: kind, inputs, sources, guidance, +5 more
Generate an operational runbook from service facts: alerts, diagnostic steps, remediation, rollback, escalation and verification. Template with explicit placeholders for what the caller did not provide.
Inputs: owner (required), alerts (required), service (required), diagnostics (required), +4 more. Returns: kind, missing, markdown, nextTools
Build a Mermaid sequence diagram from participants and ordered messages, with optional activation, notes and alt/loop blocks. Rejects unknown participants.
Inputs: title (required), messages (required), participants (required). Returns: kind, mermaid, sources, messages, +2 more
Compare curated AWS service families against user constraints. No automatic winner or fabricated scores.
Inputs: family (required), constraints. Returns: kind, options, sources, validated, +3 more
Map a cloud capability to equivalent managed services on AWS, Azure, Google Cloud, OCI and open source. Names as of the snapshot date; verify current naming, regions and pricing before deciding.
Inputs: to, from, query, categories. Returns: from, kind, rows, categories, +2 more
Calculate an availability error budget for a chosen period.
Inputs: periodDays (required), availabilityPercent (required), usedDowntimeMinutes. Returns: kind, sources, exhausted, validated, +6 more
Project storage volume and relative cost over time from ingest, retention, compression, replication and growth; suggests tiering thresholds.
Inputs: dailyIngestGB (required), retentionDays (required), months, hotDays, +5 more. Returns: kind, series, sources, tiering, +7 more
Review a Terraform or OpenTofu plan exported as JSON (terraform show -json): deletions and replacements of stateful resources, public exposure, disabled encryption, literal credentials, broad policies and unpinned providers. Any provider; heuristic.
Inputs: plan (required). Returns: gate, kind, actions, sources, +7 more
Create STRIDE review prompts for explicitly supplied assets and trust boundaries. Review aid, not a scanner.
Inputs: assets (required), boundaries (required), dataClassification (required). Returns: kind, assets, sources, threats, +4 more
Organize evidence by six pillars. A met control without evidence is unknown, never certified.
Inputs: controls (required), workload (required). Returns: kind, next, sources, summary, +5 more
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 48 tools
Most tools have a sharply distinct target artifact or computation (cost_model vs capacity_plan vs latency_budget vs queue_sizing are clearly separated), and the review tools each bind to a specific input format (CloudFormation, Terraform plan, OpenAPI, Kubernetes, MCP config). A few pairs invite confusion: aws_regions vs aws_regional_availability, service_compare vs service_equivalents vs architecture_pattern's provider mapping, and integration_catalog vs integration_config vs mcp_config_review.
Names are uniformly lower_snake_case and mostly follow a domain-noun-first pattern with an optional action suffix (iam_policy_review, cost_model, slo_budget, queue_sizing). Minor deviations exist where the verb lands mid-name (code_review_architecture, aws_knowledge_search) and some names are bare nouns while siblings are noun_verb, but nothing is ambiguous or camelCase-mixed.
48 tools is heavy even for a broad architecture-advisory domain; the surface spans cost, reliability, security, AI-agent design, IaC review and AWS docs lookup in one flat list. Without grouping or prefixes, an agent must scan a large set to find the right tool, and several near-neighbors increase selection cost.
Coverage is unusually thorough: discovery/requirements, pattern selection, ADR, Well-Architected review, capacity/cost/SLO/latency/queue math, DR, migration, diagrams (C4/sequence/Mermaid), data classification, AI-agent planning, and artifact reviews across IaC, IAM, OpenAPI, MCP config and dependencies. Gaps are minor and largely deliberate (no execution/deployment, no network/VPC topology or multi-account landing-zone design, no backup-plan generator).
Designs, prices, and deploys AWS/GCP cloud infrastructure from plain-English requirements.
Discover cloud shapes and create, inspect, validate, patch, and review architecture diagrams.
AWS pricing and cost estimates with no signup, plus read-only idle-resource scans of your account.
Simulate cloud infrastructure and estimate cost before deploying or changing infrastructure.
