Lumi App Finder

io.github.alice51849由 GitHub 账号 alice51849 发布v1.3.0更新于 Oct 27, 2026

Find Lumi Studio iOS apps by task across all 50 Apple locales, with direct App Store links.

发布方自己的服务:Finder Jobs

已验证STDIO仅桌面位置与生活商业与电商

概览

AI 生成的概览

只读 MCP 服务器,可按任务或购买需求在 50 个 Apple 语言区域中匹配 46 款 Lumi Studio iOS 应用,并给出 App Store 链接。

可以做什么
  • 用任意支持的语言,按任务、应用名称或购买需求检索内置的 46 款 Lumi Studio iOS 应用目录。
  • 选择 Apple 50 个语言区域代码之一,并将结果限制在 1 至 10 条。
  • 每条结果包含本地化说明、购买模式、详细指南以及对应商店的直接 App Store 链接。
  • 在支持 MCP Apps 扩展的宿主中显示为可交互的本地化卡片,其他宿主则获得文本与结构化数据回退结果。
适用场景
当助手需要针对用户描述的任务或需求推荐 iOS 应用,并希望提供本地化 App Store 链接时适用。它只是单一发行方的目录,适合在 Lumi Studio 自家应用范围内查找,而非通用 App Store 搜索。
运行要求
以 stdio 在本地运行;MCPB 包无需账号、API 密钥或手动配置。npx 安装方式需要 Node.js 20 或更高版本,另提供 OCI 镜像。运行时不需要网络访问。
安装前请注意
结果是发行方自行撰写的文本匹配,并非实测搜索量、独立排名、评价或用户推荐,且所有应用均出自同一发行方。运行时不会发起网络请求,也不记录查询。可选的 Agent Skill 安装器由第三方提供,默认上报匿名安装遥测。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Lumi App Finder,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

Lumi App Finder MCP

Lumi App Finder gives AI assistants one read-only tool for matching a user's task or buyer need to a verified live Lumi Studio iOS app.

It covers 46 apps × all 50 Apple locales. Every result includes editorially localized context, the purchase model, a detailed guide, and a direct App Store link for the matching storefront.

Hosts that support the stable MCP Apps extension render the matches as interactive, localized cards with one-click App Store and guide actions. Other hosts receive the same complete text and structured-data fallback.

First-party disclosure: Lumi Studio develops every listed app. Results are transparent publisher-authored text matches, not measured search volume, independent rankings, reviews, or user endorsements.

Agent Skill

AI hosts that support the open Agent Skills specification can install the same 50-locale, first-party catalog as an offline, progressively loaded skill:

bash
gh skill install alice51849/lumi-mcp lumi-app-finder --scope user

GitHub CLI 2.90 or newer installs to GitHub Copilot by default. Add --agent claude-code, --agent cursor, --agent codex, or --agent gemini-cli for another supported host. The installed skill reads only the requested locale's 46-record snapshot and requires no account, API key, network request, or executable script at runtime.

The version-pinned skill also works with the Vercel Skills CLI and its supported agents:

bash
npx -y [email protected] add https://github.com/alice51849/lumi-mcp --skill lumi-app-finder -g -y

The third-party installer reports anonymous installation telemetry by default under the skills.sh CLI policy. The installed Lumi App Finder skill itself remains offline and contains no analytics.

The public skill is discoverable on its skills.sh directory page, which reads the same first-party SKILL.md from this repository.

Lumi App Finder is also listed in the independently maintained Awesome Skills directory, which links to the published skill files.

Tool

find_ios_apps

Inputs:

  • query — task, app name, or buyer need in any supported language.
  • locale — one of Apple's 50 supported locale codes; defaults to en-US.
  • limit — 1–10 matches; defaults to 5.

The release snapshot is generated from the authoritative live publisher registry and rejected unless it contains exactly 46 unique App Store IDs × 50 Apple locales = 2,300 complete records. The runtime reads only that digest-verified bundled snapshot: it makes no network request, and user query text never leaves the local MCP process.

Install

Find io.github.alice51849/lumi-app-finder in clients or registries that use the official MCP Registry, or use a version-pinned installer:

[Install in VS Code] [Install in Cursor] [Download for Claude Desktop]

The VS Code and Cursor links run the zero-dependency server from the latest verified public GitHub release through npx; Node.js 20 or newer is required. The same configuration can be added manually:

json
{  "servers": {    "lumi-app-finder": {      "type": "stdio",      "command": "npx",      "args": [        "-y",        "https://github.com/alice51849/lumi-mcp/releases/latest/download/lumi-app-finder-npx.tgz"      ]    }  }}

The MCPB uses Node's stdio transport and needs no account, API key, external UI runtime, or manual configuration.

The source includes a multi-architecture OCI release path. Main does not advertise an OCI tag as installable until release publication verifies an existing public GHCR package, a candidate digest, ownership labels, SBOM, provenance, and a 50-locale MCP smoke test, then promotes that same digest to the public semver tag and Registry.

For Cline, use the exact configuration and verification steps in llms-install.md.

50-locale coverage

ar-SA, bn-BD, ca, cs, da, de-DE, el, en-AU, en-CA, en-GB, en-US, es-ES, es-MX, fi, fr-CA, fr-FR, gu-IN, he, hi, hr, hu, id, it, ja, kn-IN, ko, ml-IN, mr-IN, ms, nl-NL, no, or-IN, pa-IN, pl, pt-BR, pt-PT, ro, ru, sk, sl-SI, sv, ta-IN, te-IN, th, tr, uk, ur-PK, vi, zh-Hans, zh-Hant.

MCPB display metadata and the catalog output both use these localized resources.

Development

bash
npm cinpm run catalog:gatenpm run build:uinpm run build:skillnpm testnpm run smokenpm run benchmarknpm run validatenpm run validate:registrynpm run pack:mcpb

Refresh the bundled catalog and 50 locale resources from the public ios-app-guide source:

bash
npm run sync:catalog

Version tags publish the MCPB and attested multi-architecture OCI image, then update the official Registry through GitHub OIDC without long-lived registry credentials. Registry publication is the final step and cannot run before all artifact gates succeed.

Privacy

See PRIVACY.md. The runtime has zero telemetry, no analytics or tracking, no network requests, and no query, IP-address, or user-agent logging.

Security

Report vulnerabilities privately through the security policy, not through a public issue.

License

MIT. Third-party language-data notices are in THIRD_PARTY_NOTICES.txt; bundled MCP App library licenses are in MCP_APP_NOTICES.txt.

来源:README.md,提交 4c0c37f

工具

0
SourceWeft 尚未在沙箱中启动过该软件包,因此其工具未知。

版本历史

1
  1. v1.3.0最新Sep 16, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分

其他 Finder 集成