What it does
Evidence-first architecture workbench: 48 deterministic tools, 10 architect personas, any cloud
- Connects 电脑或云端
- Account or key No key needed
- Category 开发者工具
可搭配使用
教 AI 做这类工作的 Skill,可与本项一起使用
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
graphify
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
为什么排在这里
列表按使用分(满分 100)排序,由以下部分组成
| 热度 | 4/80 | GitHub 星标或每周下载量:较大的计 60,较小的计 20 |
|---|---|---|
| 新鲜度 | 12/12 | 30 天内有发布或代码更新得满分 |
| 仍在响应 | 8/8 | 上次检查时云端端点有响应 |
| 使用分 | 24/100 |
质量: 基础检查通过 5/5 项(仅展示,不用于排序) · 上升势头: 暂无数据 (只用于“上升中”标签)
安装
选择你使用的 AI 应用,然后复制设置。
用一句话让 AI 帮你安装
请帮我安装 Moretes Architect MCP。按照 https://mcp.popnx.com/i/fernando-moretes-moretes-aws-architect-mcp.md 操作,先把命令给我看,等我同意后再运行。粘贴到能在你电脑上工作的 AI(如 Claude Code、Cursor)。它会读取我们的步骤,先给你看命令,等你同意。无需密钥,无需注册。 · 查看 AI 会读取的全文
通过 5/5 项检查 · 你的提问会经过开发者的服务器(mcp.moretes.com) · ✓ 命令已检查 2026年11月13日
第一步:你用哪个 AI?
选择你用的应用,步骤会显示在下方。
可连接 Claude · 约 2 分钟
不需要密钥,不用安装程序 · 在 claude.ai 或桌面应用设置一次,即可在聊天中使用 · 免费账户可添加 1 个 · Team/Enterprise 方案由所有者(Owner)添加
打开 Claude 的 Connectors 页面
CustomizeConnectors
点击“Add” → “Custom” → “Web”,填写这 2 项
把这里的内容复制到 Claude 中同名的输入框,然后点击 Continue
Name · 名称Moretes Architect MCPRemote MCP server URL · 地址https://mcp.moretes.com/mcp在 Claude 检测到的登录设置页点击 Continue · Authentication 按作者说明选择(Sign in now、Sign in when needed 或 No sign in),然后点击 Add
在聊天中开启
+ConnectorsMoretes Architect MCP
试一试
用 Moretes Architect MCP 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude 说正在使用 Moretes Architect MCP,或回答中出现 Moretes Architect MCP 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
能否连接 ChatGPT 取决于方案
完整 MCP:网页版 ChatGPT Business、Enterprise 或 Edu · Pro:以读取/获取权限连接,修改数据的工具可能用不了 · Plus:官方文档尚未确认,如果在插件页看到添加自定义 MCP 的选项可以试试 · 仅限网页
在网页版 ChatGPT 打开添加 MCP 的页面
Plugins+Add custom MCP server
填写名称和地址
输入名称,在 Connection 下粘贴地址,勾选风险提示,然后点击 Create as a plugin
Name · 名称Moretes Architect MCPConnection · 地址https://mcp.moretes.com/mcp在聊天中选择 Moretes Architect MCP
开启新聊天,输入前先从插件列表中选择 Moretes Architect MCP
试一试
用 Moretes Architect MCP 告诉我你能帮我做什么,然后做一件给我看✓ 如果 ChatGPT 说正在使用 Moretes Architect MCP,或回答中出现 Moretes Architect MCP 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 OpenAI 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Claude Code · 约 2 分钟
不需要密钥,不用安装程序
打开终端
Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell
粘贴这条命令并按 Enter
claude mcp add --transport http --scope user moretes-aws-architect https://mcp.moretes.com/mcp在 Claude Code 中输入 /mcp
应能看到 Moretes Architect MCP 在列表中并显示已连接
试一试
用 Moretes Architect MCP 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude Code 说正在使用 Moretes Architect MCP,或回答中出现 Moretes Architect MCP 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Cursor · 约 2 分钟
不需要密钥,不用安装程序
在 Cursor 中以 Agent 模式打开 AI 聊天
试一试
用 Moretes Architect MCP 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Cursor 说正在使用 Moretes Architect MCP,或回答中出现 Moretes Architect MCP 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Cursor 帮助页面核实 · 你的界面可能因版本略有不同
可连接 VS Code · 约 2 分钟
不需要密钥,不用安装程序
在 VS Code 中以 Agent 模式打开 AI 聊天
试一试
用 Moretes Architect MCP 告诉我你能帮我做什么,然后做一件给我看✓ 如果 VS Code 说正在使用 Moretes Architect MCP,或回答中出现 Moretes Architect MCP 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 VS Code 帮助页面核实 · 你的界面可能因版本略有不同
其他支持 MCP 的应用(如 Windsurf、Zed、Gemini CLI)添加方式各不相同,请在应用列表中查看
通过网页连接的应用使用的地址
https://mcp.moretes.com/mcpJSON 设置在下方“开发者专用”中
开发者专用:终端命令和 JSON 设置
通过网页连接
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"
}
}
}安装在电脑上
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"
]
}
}
}这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
一览
哪些应用可以使用它
依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。
通过互联网连接,适用于
ClaudeChatGPTGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast
在你的电脑上运行,适用于
ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
它能做什么
工具名称和描述与服务器在 2026年11月13日 报告的完全一致。这些内容由作者撰写,不是我们写的;我们以纯文本形式显示。
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.
基础检查i
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月18日
- ✓ 通过
作者与仓库一致
注册名称已通过 GitHub 账户 fernando-moretes 验证,该账户拥有此仓库
- ✓ 通过
仍在维护
代码最后更新于10天前
- ✓ 通过
有许可证
使用 MIT
- ✓ 通过
端点有响应
在 452 毫秒内响应(HTTP 200)
- – 不适用
使用 OAuth 登录
无需登录
- ✓ 通过
工具描述中没有隐藏指令
已读取 48 个工具描述,未发现针对 AI 的隐藏指令
已公开的漏洞(OSV.dev)
OSV.dev 中没有 moretes-aws-architect-mcp@0.5.0 的记录
只检查这个版本的包本身,不包括所有依赖 · 检查于 2026年11月15日
作者:申请重新检查或报告信息错误
给作者:在 README 中加徽章
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/servers/fernando-moretes-moretes-aws-architect-mcp)讨论
提问、分享技巧或报告无法使用。按“有帮助”数量排序。
用户评价
还没有评价
与“开发者工具”中的其他服务器比较i
- 星标数多于此分类中其他 6083 个服务器的 69%
- 发布到注册中心的时间比此分类中其他 6083 个服务器的 69% 更新
- 基础检查结果等于或优于此分类中其他 6083 个服务器的 99%
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
常见问题
Moretes Architect MCP 安全吗?
它在 5 项适用的基础检查中通过了 5 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
它需要哪些密钥或代码?
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在我的电脑上运行还是在云端?
两种方式都可以:安装在你的电脑上,或者连接云端版本。
它还在维护吗?
GitHub 仓库最后更新于10天前,最新版本(0.5.0)于11天前进入注册中心。
哪些应用可以使用它?
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,因此也能用于接受远程 MCP 的应用,例如网页版 ChatGPT(Business 及以上为完整 MCP;Pro 为只读)。
有什么可以替代它?
同一分类中有:GitDiagram, Appllama, Cloudflare MCP, Omnara, Repowise
功能相近的其他选择
同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
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.
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.
| 本项 Moretes Architect MCP | GitDiagram | Appllama | Cloudflare MCP | Omnara | Repowise | |
|---|---|---|---|---|---|---|
| 运行位置 | 云端或安装在电脑上都可以 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 云端或安装在电脑上都可以 |
| 需要密钥 | 否 | 否 | 否 | 否 | 否 | 否 |
| 可在 Claude 中按 + 添加 | 否 | 否 | 否 | 是 | 否 | 否 |
| 基础检查 | 5/5 | 4/4 | 4/4 | 4/4 | 4/4 | 5/5 |
| 许可证 | MIT | MIT | MIT | Apache-2.0 | Apache-2.0 | AGPL-3.0 |
| 价格 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 |
作者的 README
打开 README
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
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." } ] }
#