原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。评价和账户功能将在后续阶段推出。
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

Cloudcraft MCP

作者:hypark5540版本 0.1.8i★ –i在你的电脑上运行
注册名称io.github.hypark5540/cloudcraft-mcp

安装

概览

作者提供的说明(英文原文)

Unofficial MCP server for reading and managing Cloudcraft architecture blueprints

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

  • 连接方式: 在你的电脑上运行
  • 传输方式: stdio
  • 分类: 其他
  • 你需要填写:CLOUDCRAFT_API_KEY

安装

选择你使用的 AI 应用,然后复制设置。

安装之前

  • 基础检查:1 项中通过 1 项
  • 在你的电脑上运行,拥有你的用户账户的权限(文件、网络、应用)。
  • 需要你自己填写: CLOUDCRAFT_API_KEY, CLOUDCRAFT_BASE_URL, CLOUDCRAFT_LOG_LEVEL, CLOUDCRAFT_EXPORT_DIR, CLOUDCRAFT_ENABLE_WRITES, CLOUDCRAFT_ENABLE_DELETES, CLOUDCRAFT_MAX_RESPONSE_BYTES

标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。

你需要

  • npm已安装 Node.js(用于 npx 命令)

你用的是哪个应用?

在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。

打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json

{
  "mcpServers": {
    "cloudcraft": {
      "command": "npx",
      "args": [
        "-y",
        "@hypark5540/cloudcraft-mcp"
      ],
      "env": {
        "CLOUDCRAFT_API_KEY": "your-value",
        "CLOUDCRAFT_BASE_URL": "your-value",
        "CLOUDCRAFT_LOG_LEVEL": "your-value",
        "CLOUDCRAFT_EXPORT_DIR": "your-value",
        "CLOUDCRAFT_ENABLE_WRITES": "your-value",
        "CLOUDCRAFT_ENABLE_DELETES": "your-value",
        "CLOUDCRAFT_MAX_RESPONSE_BYTES": "your-value"
      }
    }
  }
}

在终端中运行这条命令

claude mcp add cloudcraft --env CLOUDCRAFT_API_KEY=your-value --env CLOUDCRAFT_BASE_URL=your-value --env CLOUDCRAFT_LOG_LEVEL=your-value --env CLOUDCRAFT_EXPORT_DIR=your-value --env CLOUDCRAFT_ENABLE_WRITES=your-value --env CLOUDCRAFT_ENABLE_DELETES=your-value --env CLOUDCRAFT_MAX_RESPONSE_BYTES=your-value -- npx -y @hypark5540/cloudcraft-mcp

运行前请先填写空着的值。

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "cloudcraft": {
      "command": "npx",
      "args": [
        "-y",
        "@hypark5540/cloudcraft-mcp"
      ],
      "env": {
        "CLOUDCRAFT_API_KEY": "your-value",
        "CLOUDCRAFT_BASE_URL": "your-value",
        "CLOUDCRAFT_LOG_LEVEL": "your-value",
        "CLOUDCRAFT_EXPORT_DIR": "your-value",
        "CLOUDCRAFT_ENABLE_WRITES": "your-value",
        "CLOUDCRAFT_ENABLE_DELETES": "your-value",
        "CLOUDCRAFT_MAX_RESPONSE_BYTES": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "cloudcraft": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@hypark5540/cloudcraft-mcp"
      ],
      "env": {
        "CLOUDCRAFT_API_KEY": "your-value",
        "CLOUDCRAFT_BASE_URL": "your-value",
        "CLOUDCRAFT_LOG_LEVEL": "your-value",
        "CLOUDCRAFT_EXPORT_DIR": "your-value",
        "CLOUDCRAFT_ENABLE_WRITES": "your-value",
        "CLOUDCRAFT_ENABLE_DELETES": "your-value",
        "CLOUDCRAFT_MAX_RESPONSE_BYTES": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。

这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。

你的选择通过 Cookie 保存在这台设备上,无需账户。

需要你填写的值

  • CLOUDCRAFT_API_KEY 机密 必填 env
    Cloudcraft API key with access to the target account
  • CLOUDCRAFT_BASE_URL env
    Cloudcraft API base URL; HTTPS is required except for loopback testing
  • CLOUDCRAFT_LOG_LEVEL env
    Minimum log level written to stderr
  • CLOUDCRAFT_EXPORT_DIR env
    Directory under which exported blueprint files may be written
  • CLOUDCRAFT_ENABLE_WRITES env
    Enable create and update operations
  • CLOUDCRAFT_ENABLE_DELETES env
    Enable irreversible deletes; writes must also be enabled
  • CLOUDCRAFT_MAX_RESPONSE_BYTES env
    Maximum bytes accepted from one Cloudcraft API response

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。

它能做什么

它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。

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7日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过 GitHub 账户 hypark5540 验证,该账户拥有此仓库

  • … 尚未检查

    仍在维护

    我们还没有从 GitHub 读取这个仓库

  • … 尚未检查

    有许可证

    我们还没有从 GitHub 读取这个仓库

  • – 不适用

    端点有响应

    它在你的电脑上运行,没有互联网端点

  • – 不适用

    使用 OAuth 登录

    在你的电脑上运行,改用本地设置

  • … 尚未检查

    工具描述中没有隐藏指令

    它在你的电脑上运行;我们只能读取互联网端点的工具列表

与“其他”中的其他服务器比较i

  • 星标数多于此分类中其他 32583 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 32583 个服务器的 68% 更新
  • 基础检查结果等于或优于此分类中其他 32583 个服务器的 100%

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

Cloudcraft MCP 安全吗?

它在 1 项适用的基础检查中通过了 1 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?

你需要填写:CLOUDCRAFT_API_KEY

它在我的电脑上运行还是在云端?

它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。

它还在维护吗?

GitHub 仓库最后更新于–,最新版本(0.1.8)于17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。你的电脑上还需要有 Node.js, Python (uv), Docker。

有什么可以替代它?

同一分类中有:Spec Driven Development, Remote Desktop Commander, sync. labs

替代选择

同一分类中其他作者的服务器,按星标数排序。

如何看卡片:★ 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

Spec Driven Development

作者:formulahendry

MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.

在你的电脑上运行★ 440MIT14个月前更新
安装

Remote Desktop Commander

作者:desktop-commander

Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.

在云端运行★ 211昨天更新
安装

sync. labs

作者:synchronicity-labs

Lipsync videos, dub them into other languages, make talking videos and open sync. Studio.

电脑或云端今天更新
安装

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。

cloudcraft-mcp

Unofficial Model Context Protocol (MCP) server for Cloudcraft — list, read, export, and build cloud architecture blueprints from Claude Desktop and other MCP clients.

Features

Thirteen tools exposed to the MCP host:

ToolDescription
whoamiReturn the Cloudcraft user profile for the configured key.
list_blueprintsList every blueprint in the account.
get_blueprintFetch a blueprint's full node / edge JSON.
create_blueprintCreate a new blueprint from a JSON payload.
update_blueprintReplace an existing blueprint's payload.
delete_blueprintDelete a blueprint (irreversible).
export_blueprint_imageRender a blueprint to PNG / SVG / PDF / mxgraph on disk.
export_blueprint_budgetExport a blueprint's cost estimate as CSV / XLSX on disk.
list_teamsList teams linked to the account.
list_aws_accountsList AWS accounts connected for live-scan snapshots.
snapshot_awsLive-scan one AWS region into blueprint JSON (optional filter / exclude).
list_azure_accountsList Azure accounts connected for live-scan snapshots.
snapshot_azureLive-scan one Azure region into blueprint JSON (optional filter / exclude).

Requirements

  • uv for the recommended uvx and npm launchers
  • Node.js 22+ only when using the npm launcher
  • Cloudcraft API key — generate one at https://app.cloudcraft.co/ → User settings → API keys

Install

Use an immutable version in client configuration so upgrades are deliberate.

ChannelCommand
PyPI / uvxuvx --from cloudcraft-mcp==0.1.8 cloudcraft-mcp
pipxpipx run --spec cloudcraft-mcp==0.1.8 cloudcraft-mcp
npm / npxnpx -y @hypark5540/cloudcraft-mcp@0.1.8
Docker / GHCRdocker run --rm -i -e CLOUDCRAFT_API_KEY ghcr.io/hypark5540/cloudcraft-mcp:0.1.8
Claude DesktopDownload cloudcraft-mcp.mcpb from the matching GitHub release

uvx is delivered by the PyPI package; there is no separate uvx registry. The npm package embeds the byte-identical Python wheel and invokes it through uv, so the npm path requires both Node.js and uv. It does not download code in a postinstall hook.

For development from a checkout:

git clone https://github.com/hypark5540/cloudcraft-mcp.git

cd cloudcraft-mcp export CLOUDCRAFT_API_KEY='your-key-here' uv run --frozen cloudcraft-mcp # Ctrl+C to exit

Claude Desktop integration

Install uv, then add this entry to Claude Desktop's configuration. Prefer Claude's secret storage when available; the literal below is only a portable example.

{

"mcpServers": { "cloudcraft": { "command": "uv", "args": [ "tool", "run", "--isolated", "--from", "cloudcraft-mcp==0.1.8", "cloudcraft-mcp" ], "env": { "CLOUDCRAFT_API_KEY": "your-key-here", "CLOUDCRAFT_ENABLE_WRITES": "false", "CLOUDCRAFT_ENABLE_DELETES": "false" } } } }

Restart Claude Desktop. The Developer tab should show cloudcraft as connected.

See client setup for Cursor, Gemini CLI, npm, Docker, and MCPB examples.

Environment variables
NameRequiredDefaultPurpose
CLOUDCRAFT_API_KEYyes—API key (Bearer). Generated in Cloudcraft User settings.
CLOUDCRAFT_BASE_URLnohttps://api.cloudcraft.coOverride for proxies or future API versions.
CLOUDCRAFT_LOG_LEVELnoWARNINGStderr log verbosity (DEBUG / INFO / WARNING / ERROR).
CLOUDCRAFT_EXPORT_DIRnoprivate temp subdirectoryDirectory that export_blueprint_image may write under.
CLOUDCRAFT_ENABLE_WRITESnofalsePermit create_blueprint and update_blueprint.
CLOUDCRAFT_ENABLE_DELETESnofalsePermit deletes when writes are also enabled.
CLOUDCRAFT_MAX_RESPONSE_BYTESno26214400Reject oversized Cloudcraft responses before they exhaust memory or disk.

Usage examples (in Claude)

Once the server is connected, ask Claude things like:

*"List my Cloudcraft blueprints and summarize what each represents."*

*"Export blueprint f0086b32-... as PNG and save it to my Desktop."*

*"Take the architecture I just designed and create a new Cloudcraft blueprint called 'Prod 2026'."*

*"Snapshot ap-northeast-2 of my connected AWS account, excluding security groups."*

*"Export the monthly budget of blueprint f0086b32-... as CSV in EUR."*

Blueprint payload shape

create_blueprint / update_blueprint accept the full Cloudcraft data object. A minimal payload:

{

"grid": "infinite", "projection": "isometric", "theme": {"base": "light"}, "version": 6, "nodes": [ {"id": "...", "type": "ec2", "mapPos": [3, 3], "region": "ap-northeast-2", "instanceType": "m7g", "instanceSize": "large", "platform": "linux"}, {"id": "...", "type": "s3", "mapPos": [1, 8], "region": "ap-northeast-2", "volumeType": "Standard", "dataGb": 100} ], "edges": [ {"from": "...ec2-id...", "to": "...s3-id...", "type": "edge", "width": 2, "dashed": false, "endCap": "arrow"} ], "groups": [], "surfaces": [], "text": [], "icons": [], "connectors": [], "images": [], "disabledLayers": [], "shareDocs": false }

Refer to Cloudcraft's API docs for the full node-type catalog and service-specific fields.

Development

uv sync --extra dev

uv run pytest # unit tests (no network) uv run ruff check . # lint uv run mypy src # type check

Tests mock the HTTP layer with respx so no API key is required.

Coverage

CI uploads coverage.xml from the Python 3.12 matrix cell to Codecov. The project gate is 80% or higher — a PR that drops overall or patch coverage by more than 1 percentage point below that line fails the Codecov check (codecov.yml).

Run the same report locally:

uv run pytest --cov=cloudcraft_mcp --cov-report=term-missing --cov-report=xml
Project layout
cloudcraft-mcp/

├── src/cloudcraft_mcp/ │ ├── init.py │ ├── main.py # python -m cloudcraft_mcp │ ├── server.py # MCP tool definitions (FastMCP) │ ├── client.py # CloudcraftClient — async httpx wrapper │ ├── types.py # TypedDicts for blueprint payloads │ └── py.typed ├── tests/ │ └── test_client.py ├── bin/cloudcraft-mcp.mjs # npm-to-uv launcher ├── mcpb/manifest.json # Claude Desktop bundle metadata ├── server.json # official MCP Registry metadata ├── package.json # npm distribution ├── server.py # back-compat shim -> cloudcraft_mcp.server:main ├── pyproject.toml ├── LICENSE └── README.md

Design notes

  • Transport / logic split. client.py is a plain async HTTP client you can import from scripts or CLI tools without pulling the MCP runtime. server.py only owns the MCP tool surface.
  • Bearer-token auth. Cloudcraft's API expects Authorization: Bearer (not Apikey). The client sets this automatically.
  • No secrets in process args. The API key is read from CLOUDCRAFT_API_KEY; never pass it on the command line.
  • One implementation. PyPI, npm, MCPB, and the container all launch the same versioned Python package rather than maintaining language-specific forks.
  • Error surface. Non-2xx responses raise CloudcraftError with status and body preserved, re-wrapped as RuntimeError at the MCP boundary so Claude sees a readable message.

Security

  • API keys grant full read / write over your Cloudcraft account. Treat them as secrets and rotate regularly.
  • MCP tool annotations mark read-only tools and mutating/destructive tools so compatible hosts can present better approval prompts. These annotations are hints, not an enforcement layer.
  • Environment gates and exact-ID delete confirmation are defense in depth, not an interactive approval workflow; keep the MCP host's tool approval UX enabled.
  • Cloudcraft mutations are disabled by default. Set CLOUDCRAFT_ENABLE_WRITES=true only for clients that need create/update access. Deletes additionally require CLOUDCRAFT_ENABLE_DELETES=true and an exact repeated blueprint ID on every call.
  • delete_blueprint is irreversible — when asking Claude to delete, be explicit about the target id.
  • export_blueprint_image writes are sandboxed under CLOUDCRAFT_EXPORT_DIR (a process-private temporary subdirectory by default) and refuse to overwrite existing files unless overwrite=True.
  • For read-heavy setups, create a dedicated Cloudcraft user with read-only scope (if/when Cloudcraft adds scoped keys) and use that key for MCP.
  • Supported versions and private reporting instructions are in SECURITY.md; data flow is documented in PRIVACY.md.

Contributing

Issues and PRs welcome at https://github.com/hypark5540/cloudcraft-mcp. Please run ruff, mypy, and pytest before submitting.

License

MIT — see LICENSE.

Related

问 PopNx