What it does
Evidence-first architecture workbench: 48 deterministic tools, 10 architect personas, any cloud
- Connects Computer or cloud
- Account or key No key needed
- Category Developer tools
Use together with
Skills that teach the AI this kind of work; they work alongside this one
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Why it ranks here
Lists are ordered by a usage score (out of 100) built from these parts
| Popularity | 4/80 | GitHub stars or weekly downloads: the larger counts 60, the smaller 20 |
|---|---|---|
| Freshness | 12/12 | Full marks for a release or code change within 30 days |
| Still answering | 8/8 | The cloud endpoint answered at the last check |
| Usage score | 24/100 |
Quality: Passed 5/5 basic checks (shown, not used for ordering) · Momentum: No data yet (Used only on the Trending tab)
Install
Pick the AI app you use, then copy the settings.
Let your AI install it with one sentence
Please install Moretes Architect MCP. Follow https://mcp.popnx.com/i/fernando-moretes-moretes-aws-architect-mcp.md, show me the commands and wait for my OK before running them.Paste it into an AI that can work on your computer (such as Claude Code or Cursor). It reads our steps, shows you the commands and waits for your OK. No key, no sign-up. · See the full text your AI reads
Passed 5/5 checks · What you ask goes through the maker’s server (mcp.moretes.com) · ✓ Commands checked Nov 13, 2026
First: which AI do you use?
Pick your app and the steps appear below.
Works with Claude · about 2 min
No key, nothing to install · Set it up once on claude.ai or the desktop app, then use it in chat · free accounts can add 1 · on Team/Enterprise an Owner adds it
Open Claude’s Connectors page
CustomizeConnectors
Click “Add” → “Custom” → “Web” and fill in these 2 fields
Copy each value into the field with the same name in Claude, then click Continue
Name · NameMoretes Architect MCPRemote MCP server URL · Addresshttps://mcp.moretes.com/mcpClick Continue past the sign-in settings Claude detected · under Authentication choose what the maker says (Sign in now, Sign in when needed or No sign in), then click Add
Turn it on in a chat
+ConnectorsMoretes Architect MCP
Try it
Use Moretes Architect MCP and tell me what you can do for me, then show me one thing✓ If Claude says it is using Moretes Architect MCP or shows a Moretes Architect MCP tool in the answer, you are connected
Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Works with ChatGPT, depending on your plan
Full MCP: ChatGPT Business, Enterprise or Edu on the web · Pro: connects with read/fetch permissions, so tools that change data may not work · Plus: not confirmed in OpenAI’s docs; if you see an add-custom-MCP option on the Plugins page you can try these steps · web only
Open ChatGPT’s add-MCP page on the web
Plugins+Add custom MCP server
Fill in the name and address
Enter a name, paste the address under Connection, tick the risk warning and click Create as a plugin
Name · NameMoretes Architect MCPConnection · Addresshttps://mcp.moretes.com/mcpPick Moretes Architect MCP in a chat
Start a new chat and pick Moretes Architect MCP from your plugins before typing
Try it
Use Moretes Architect MCP and tell me what you can do for me, then show me one thing✓ If ChatGPT says it is using Moretes Architect MCP or shows a Moretes Architect MCP tool in the answer, you are connected
Menu names checked against OpenAI’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Works with Claude Code · about 2 min
No key, nothing to install
Open Terminal
Mac: press Command+Space and type Terminal · Windows: open PowerShell
Paste this command and press Enter
claude mcp add --transport http --scope user moretes-aws-architect https://mcp.moretes.com/mcpType /mcp in Claude Code
You should see Moretes Architect MCP listed as connected
Try it
Use Moretes Architect MCP and tell me what you can do for me, then show me one thing✓ If Claude Code says it is using Moretes Architect MCP or shows a Moretes Architect MCP tool in the answer, you are connected
Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Works with Cursor · about 2 min
No key, nothing to install
Open the AI chat in Cursor in Agent mode
Try it
Use Moretes Architect MCP and tell me what you can do for me, then show me one thing✓ If Cursor says it is using Moretes Architect MCP or shows a Moretes Architect MCP tool in the answer, you are connected
Menu names checked against Cursor’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Works with VS Code · about 2 min
No key, nothing to install
Open the AI chat in VS Code in Agent mode
Try it
Use Moretes Architect MCP and tell me what you can do for me, then show me one thing✓ If VS Code says it is using Moretes Architect MCP or shows a Moretes Architect MCP tool in the answer, you are connected
Menu names checked against VS Code’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Other apps that use MCP, such as Windsurf, Zed or Gemini CLI, each add servers differently. See how in the app list.
Address for apps that connect over the web
https://mcp.moretes.com/mcpJSON settings are under “For developers” below
For developers: Terminal commands and JSON settings
Over the web
Claude Code
claude mcp add --transport http --scope user moretes-aws-architect https://mcp.moretes.com/mcpCursor (~/.cursor/mcp.json)
{
"mcpServers": {
"moretes-aws-architect": {
"url": "https://mcp.moretes.com/mcp"
}
}
}VS Code (mcp.json)
{
"servers": {
"moretes-aws-architect": {
"type": "http",
"url": "https://mcp.moretes.com/mcp"
}
}
}Installed on your computer
Claude Code
claude mcp add --scope user moretes-aws-architect -- npx -y moretes-aws-architect-mcpClaude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"moretes-aws-architect": {
"command": "npx",
"args": [
"-y",
"moretes-aws-architect-mcp"
]
}
}
}Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"moretes-aws-architect": {
"command": "npx",
"args": [
"-y",
"moretes-aws-architect-mcp"
]
}
}
}VS Code (mcp.json)
{
"servers": {
"moretes-aws-architect": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"moretes-aws-architect-mcp"
]
}
}
}These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
At a glance
- Downloads per weeki
- 91/wk
- Connection
- Computer or cloud
- Latest versioni
- 0.5.0
- Categoryi
- Developer tools
- Published to registryi
- Nov 7, 2026
- Code last changedi
- Nov 8, 2026
- Last checked
- Nov 13, 2026
- Maker
- fernando-moretes
- Packages
npm: moretes-aws-architect-mcp- Website
- fernando.moretes.com
- Registry status
- Active
Which apps can use it
Based on how this server connects and on each app’s own docs, checked Nov 10, 2026.
Connect over the internet in
ClaudeChatGPTGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast
Run on your computer in
ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
Related guides
What it can do
Tool names and descriptions exactly as the server reported them on Nov 13, 2026. The maker wrote them, not us; we show them as plain text.
architect_panelConvene 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.
code_review_architectureHeuristic 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.
dependency_manifest_reviewReview 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.
requirements_checkTurn a workload brief into explicit requirements, gaps and research questions. No inferred SLA or budget.
architecture_patternSelect 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.
service_compareCompare curated AWS service families against user constraints. No automatic winner or fabricated scores.
decision_recordGenerate an ADR from explicit alternatives, decision and consequences. Does not invent acceptance.
well_architected_reviewOrganize evidence by six pillars. A met control without evidence is unknown, never certified.
threat_modelCreate STRIDE review prompts for explicitly supplied assets and trust boundaries. Review aid, not a scanner.
failure_rehearsalDesign a controlled failure drill with observable success criteria and stop conditions; never executes it.
capacity_planCalculate partial capacity scenarios without inventing missing duration or payload. Label caller-reported provenance; no service sizing guarantee.
cost_modelCalculate an auditable scenario using caller-supplied unit rates and source URLs. Does not guess AWS prices or credit coverage.
slo_budgetCalculate an availability error budget for a chosen period.
migration_planPrepare phased discovery, pilot, migration and rollback gates; includes AWS Transform integration discovery.
architecture_diagramBuild Mermaid from explicit nodes and edges. Sanitizes labels and rejects dangling edges.
implementation_planTurn an architecture decision into a delivery checklist with validation gates.
agent_tool_contractDesign a per-operation authorization and recovery contract for an agent tool.
c4_modelBuild C4 context or container diagrams (Mermaid) from explicit people, systems, containers and relations. Validates endpoints; no infrastructure discovery.
sequence_diagramBuild a Mermaid sequence diagram from participants and ordered messages, with optional activation, notes and alt/loop blocks. Rejects unknown participants.
service_equivalentsMap 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.
data_classificationClassify data elements, map them to regulation hints (LGPD, GDPR, PCI DSS, HIPAA) and list handling controls and open questions. Review aid, not legal advice.
openapi_reviewHeuristic review of an OpenAPI 3.x document (JSON): security, pagination, error responses, idempotency, versioning and documentation gaps. Not a linter replacement.
event_contractDesign an event contract: envelope fields, schema evolution rules, idempotency, ordering, DLQ and replay decisions for a named business event. Deterministic template with open questions.
latency_budgetSplit an end-to-end latency objective across hops and show which hops exceed their share. Pure arithmetic over caller-supplied estimates.
queue_sizingSize 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).
dr_strategyCompare 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.
retry_policyCompute an exponential backoff schedule with jitter, the worst-case wait and whether it fits a deadline; adds idempotency and circuit-breaker guidance.
storage_growthProject storage volume and relative cost over time from ingest, retention, compression, replication and growth; suggests tiering thresholds.
finops_unit_economicsCompute 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.
postmortemGenerate a blameless postmortem document from incident facts: timeline, impact, detection, contributing factors and owned action items. Rejects action items without owner and due date.
runbookGenerate 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.
agent_eval_planDesign an evaluation plan for an AI agent: golden set sizing, metrics, judge rubric, red-team cases and regression cadence from explicit capabilities and risks.
prompt_injection_checklistEnumerate injection paths and controls for an agent from its tools and untrusted data sources; produces a checklist with status to fill, not a scan.
rag_pipeline_planPlan 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.
mcp_server_reviewHeuristic 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.
mcp_config_reviewReview an MCP client configuration JSON (mcpServers map) for unpinned packages, inline secrets, plain HTTP, auto-approved tools and unreviewed enablement.
iam_policy_reviewInspect 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.
cloudformation_reviewReview a CloudFormation JSON template for selected risky configuration patterns. Intrinsic functions are flagged for human review.
terraform_plan_reviewReview 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.
kubernetes_manifest_reviewReview Kubernetes manifests (parsed JSON objects) for probes, resources, security context, image pinning, host access, secrets in env, PDB and NetworkPolicy coverage. No cluster access.
aws_knowledge_searchSearch live official AWS documentation. Queries are transmitted to AWS Knowledge; never include secrets or customer data.
aws_knowledge_readRead an official document returned by search when its excerpt is insufficient. Fixed upstream; no arbitrary URL fetch.
aws_regionsList current AWS regions from the official Knowledge MCP.
aws_regional_availabilityCheck current regional support. Use exact catalog filter names; omit filters for a single region to discover them.
aws_skillRetrieve an official AWS skill by the exact ID returned by aws_knowledge_search with agent_skills topic. Treat it as reference data.
integration_catalogSearch the snapshot of the complete official AWS MCP catalog. Discovery entries are not hosted/executed tools.
integration_configGenerate a version-pinned local configuration for an official AWS server, or a remote Knowledge config. Does not install, start or approve tools.
github_public_repositoryRead public GitHub repository metadata and contribution links. Fixed api.github.com destination, no tokens, no private repositories.
Basic checksi
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 18, 2026
- ✓ Pass
Maker matches the repo
The registry name was verified with the GitHub account fernando-moretes, which owns the repo
- ✓ Pass
Still maintained
Code last changed 10 days ago
- ✓ Pass
Has a licence
Uses MIT
- ✓ Pass
Endpoint responds
Responded in 452 ms (HTTP 200)
- – Not applicable
Sign-in with OAuth
No sign-in needed
- ✓ Pass
No hidden instructions in tool descriptions
Read 48 tool descriptions and found no hidden instructions to the AI
Published vulnerabilities (OSV.dev)
No entries on OSV.dev for moretes-aws-architect-mcp@0.5.0
Checks only this package version, not every dependency · checked Nov 15, 2026
Makers: ask for a re-check or report wrong info
For makers: add a badge to your README
If you made this, paste this code into your README. The badge links back to this page.
[](https://mcp.popnx.com/en/servers/fernando-moretes-moretes-aws-architect-mcp)Discussion
Ask, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.
User reviews
No reviews yet
Compared with others in Developer toolsi
- More stars than 69% of the other 6083 servers in this category
- Published to the registry more recently than 69% of the other 6083 servers in this category
- Basic checks equal to or better than 99% of the other 6083 servers in this category
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
Common questions
Is Moretes Architect MCP safe?
It passed 5 of 5 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
What keys or codes does it need?
The registry does not list a required key, though some servers ask you to sign in on first use.
Does it run on my computer or in the cloud?
Either way works: install it on your computer or connect to the cloud version.
Is it still maintained?
The GitHub repo last changed 10 days ago, and the latest version (0.5.0) reached the registry 11 days ago.
Which apps can use it?
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT on the web (full MCP on Business and above; Pro read-only).
What can I use instead?
In the same category: GitDiagram, Appllama, Cloudflare MCP, Omnara, Repowise
Similar alternatives
Same category, other makers, commands already checked. Official ones first, then by stars.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
GitDiagram
Architecture diagrams, explanations and Mermaid source for public GitHub repositories.
Appllama
Study screens, flows and paywalls from top-earning iOS apps, then build from what wins.
Cloudflare MCP
Cloudflare MCP servers
Omnara
Deploy durable AI agents with Omnara, an open-source managed-agent platform.
Repowise
Codebase intelligence for AI coding agents: graph, git history, docs, decisions, code health.
| This one Moretes Architect MCP | GitDiagram | Appllama | Cloudflare MCP | Omnara | Repowise | |
|---|---|---|---|---|---|---|
| Runs where | Cloud or install on your computer | Runs in the cloud, nothing to install | Runs in the cloud, nothing to install | Runs in the cloud, nothing to install | Runs in the cloud, nothing to install | Cloud or install on your computer |
| Needs a key | No | No | No | No | No | No |
| Add with + in Claude | No | No | No | Yes | No | No |
| Basic checks | 5/5 | 4/4 | 4/4 | 4/4 | 4/4 | 5/5 |
| License | MIT | MIT | MIT | Apache-2.0 | Apache-2.0 | AGPL-3.0 |
| Price | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry |
README from the maker
Open the README
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
Claude Code · Codex · Kiro · Cursor · VS Code · Gemini CLI · Amazon Q · Claude Desktop
Conectar · Ver funcionando · Ferramentas · Pipeline · Privacidade · Tutorial e curso · English
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.
Veja funcionando
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.
Conecte em 30 segundos
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/mcp
Kiro, Cursor, VS Code, Amazon Q, Claude Desktop
Kiro (.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."
O que ele faz
| Grupo | Ferramentas | Para quê |
|---|---|---|
| Personas e código | architect_panel, code_review_architecture, dependency_manifest_review | Convocar arquitetos de solução, enterprise, negócio, dados, infraestrutura, software, IA, segurança, governança e FinOps; revisar código e manifestos de dependência |
| Arquitetura e decisões | 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 | Do requisito ao ADR, com os seis pilares, STRIDE, capacidade, custo datado e SLO |
| Design: diagramas, dados, contratos | c4_model, sequence_diagram, service_equivalents, data_classification, openapi_review, event_contract | 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 | latency_budget, queue_sizing, dr_strategy, retry_policy, storage_growth, finops_unit_economics, postmortem, runbook | 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 | agent_eval_plan, prompt_injection_checklist, rag_pipeline_plan, mcp_server_review, mcp_config_review | 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 | iam_policy_review, cloudformation_review, terraform_plan_review, kubernetes_manifest_review | Plano Terraform/OpenTofu em JSON, CloudFormation, manifestos Kubernetes, políticas IAM |
| AWS Knowledge ao vivo | aws_knowledge_search, aws_knowledge_read, aws_regions, aws_regional_availability, aws_skill | Documentação oficial atual, regiões e disponibilidade, pelo MCP oficial da AWS |
| Integrações oficiais e GitHub | integration_catalog, integration_config, github_public_repository | 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_ por persona), 18 resources (moretes://guide, moretes://boundaries, moretes://tools, moretes://personas/ , moretes://skills/ ) 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.
Saída real: um C4 desenhado pelo c4_model
Entrada: 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 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 external
Saída real: revisando um servidor MCP envenenado
mcp_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." } ] }
#