Vischeck

io.github.CloudCorpRecords由 GitHub 账号 CloudCorpRecords 发布v0.1.0更新于 Nov 7, 2026

See whether ChatGPT, Claude and Gemini recommend a startup product, and who wins instead.

概览

AI 生成的概览

连接 FrontStat 的本地桥接服务,让助手查询 ChatGPT、Claude 和 Gemini 是否推荐某产品,以及它们改推荐了哪些竞品。

可以做什么
  • 按域名查询已被收录的产品发布:发布榜排名、可见度分数、各 AI 引擎是否推荐,并附公开页面链接
  • 读取最新的 Pro 报告:可见度分数、各引擎的推荐情况,以及每个买家问题下有多少回答推荐你
  • 列出 FrontStat 向各 AI 引擎提问的买家问题,并给出每个引擎的推荐与否
  • 查看引擎改推荐了哪些竞品和网站,以及被引用最多的网站
  • 按天查看最近 30 天的可见度分数与推荐回答数量
适用场景
适合想了解自家产品在 AI 搜索回答中曝光情况、哪些竞品或页面更占优势的创业者或市场人员,也适合用来观察调整后数据是否变化。
运行要求
通过 npx(需 Node.js)或 Docker 在本地以 stdio 运行,调用会转发到 FrontStat 的托管端点,可用可选的 FRONTSTAT_MCP_URL 覆盖该端点。公开的发布查询无需令牌;五个 Pro 报告工具需要 FrontStat Pro 仪表盘令牌,通过可选的 FRONTSTAT_API_KEY 环境变量以 Bearer 头传递。需要网络访问。
安装前请注意
Pro 工具需要把 FrontStat Pro 仪表盘令牌放入 FRONTSTAT_API_KEY,并以 Bearer 头转发给上游端点;若设置 FRONTSTAT_MCP_URL,该令牌会发送到你指定的端点。报告数据仅覆盖订阅中的域名。所有工具均为只读;README 说明端点覆盖与令牌转发属于重建部分,并非原始抓取到的接口。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Vischeck,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

vischeck

vischeck is a small local bridge to FrontStat's hosted MCP server, which tracks whether the AI search engines recommend a startup's product. Ask about a launch, and the answer shows a visibility score and whether ChatGPT, Claude and Gemini name the product for its buyer question — or which competing products they name instead.

The bridge keeps no visibility data of its own. It serves the upstream server's tool list locally, exactly as captured from the live endpoint, and forwards each tool call upstream, returning the result untouched. The whole captured surface only reads: a public launch lookup that needs no token, plus five Pro report views that need a FrontStat Pro dashboard token.

Tools

  • check_public_launch — look up a product launch that FrontStat already tracks: its name, its rank on this week's or this month's launch board, its visibility score (0 to 100), and whether ChatGPT, Claude and Gemini recommend it for its buyer question, with the products they name instead, plus a link to its public FrontStat page. If the domain is not tracked yet, it says so and links to the free report. Required: domain (the product's domain or URL, e.g. example.com). No token needed.
  • get_visibility — your latest FrontStat Pro report: date, visibility score, whether each AI search engine recommends your product for your main buyer question and who it names instead, and per buyer question how many answers recommend you (X of Y) per assistant. Needs a Pro token. Takes no arguments.
  • list_buyer_questions — each buyer question FrontStat asks the AI search engines about your market, with a yes or no per engine for whether the answer recommends your product. Needs a Pro token. Takes no arguments.
  • who_wins_instead — the products the AI search engines name instead of yours, and the sites they cite, each with how many answers it appears in, from your latest Pro report. Needs a Pro token. Takes no arguments.
  • cited_sites — the sites the AI search engines cite most when they answer your buyer questions, with how many answers cite each one, your own domain left out: the pages to get mentioned on. Needs a Pro token. Takes no arguments.
  • visibility_history — one point per day for the last 30 days: your visibility score and how many answers recommend your product, so you can see whether your changes moved the AI search engines. Needs a Pro token. Takes no arguments.

Configuration

  • FRONTSTAT_MCP_URL (optional) — override the upstream endpoint. Defaults to https://frontstat.com/api/mcp. (The override hook is this rebuild's own labelled reconstruction.)
  • FRONTSTAT_API_KEY (optional) — when set, every upstream request carries an Authorization: Bearer <value> header, which is how the five Pro tools receive the dashboard token. When it is not set, no Authorization header is sent and only the public launch lookup works. (This forwarding is also a labelled reconstruction; the original surface was captured keyless.)

Forwarding mechanics

On the first tool call the client opens a streamable HTTP session with the upstream: a JSON-RPC initialize request (protocolVersion 2025-03-26, clientInfo name vischeck), then a notifications/initialized notification, then the tools/call request carrying the caller's arguments unchanged. When the upstream answers initialize with an Mcp-Session-Id header, that value rides on every later request of the session, which is reused for the life of the process. Replies may arrive as plain JSON or as server-sent events; both are read.

Successful upstream results pass through verbatim, including any isError flag the upstream sets. Failures — a JSON-RPC error, a non-2xx status, an unreadable response, or a request that cannot be completed — come back as an isError result whose text starts with vischeck error: (this rendering is this rebuild's own labelled reconstruction).

CLI

Each tool is also a subcommand taking one JSON argument string (omit it for tools that take none):

bash
npx @reneturcios/vischeck check_public_launch '{"domain":"example.com"}'npx @reneturcios/vischeck get_visibilitynpx @reneturcios/vischeck who_wins_instead '{}'npx @reneturcios/vischeck visibility_historynpx @reneturcios/vischeck --version

Exit codes: 0 on success, 1 on an isError result, 2 on a usage error.

MCP server

bash
npx -y @reneturcios/vischeck mcp

MCP client config:

json
{  "mcpServers": {    "vischeck": {      "command": "npx",      "args": ["-y", "@reneturcios/vischeck", "mcp"]    }  }}

Docker

bash
docker run -i ghcr.io/cloudcorprecords/vischeckdocker run --rm ghcr.io/cloudcorprecords/vischeck --version

The container's default command is mcp, so the first form is a stdio MCP server; any other arguments reach the CLI normally.

Development

bash
npm installnpm run buildnpm testnpm run dev

The test suite runs entirely against a stubbed JSON-RPC upstream — no live network calls.

License

MIT — see LICENSE.

来源:README.md,提交 9af806d

工具

6

check_public_launch

Check a launch FrontStat tracks

Look up a product launch that FrontStat already tracks: its name, its rank on this week's or this month's launch board, its visibility score (0 to 100), and whether ChatGPT, Claude and Gemini recommend it for its buyer question, with the products they name instead. Returns a link to its public FrontStat page. If FrontStat does not track the domain yet, says so and links to the free report. No token needed.

输入参数domain必填

get_visibility

Your AI visibility today

Your latest FrontStat Pro report: date, visibility score, whether each AI search engine recommends your product for your main buyer question and who it names instead, and for your buyer questions how many answers recommend you (X of Y) per assistant. Needs FrontStat Pro: send your dashboard token as a Bearer token. Covers the domain on your subscription.

无需输入参数。

list_buyer_questions

Your buyer questions

Each buyer question FrontStat asks the AI search engines about your market, with yes or no per engine: does the answer recommend your product. Needs FrontStat Pro: send your dashboard token as a Bearer token. Covers the domain on your subscription.

无需输入参数。

who_wins_instead

Who wins instead of you

The products the AI search engines name instead of yours, and the sites they cite, each with how many answers it appears in, from your latest Pro report. Needs FrontStat Pro: send your dashboard token as a Bearer token. Covers the domain on your subscription.

无需输入参数。

cited_sites

Sites AI search engines cite

The sites the AI search engines cite most when they answer your buyer questions, with how many answers cite each one, your own domain left out. These are the pages to get mentioned on. Needs FrontStat Pro: send your dashboard token as a Bearer token. Covers the domain on your subscription.

无需输入参数。

visibility_history

Your visibility over 30 days

One point per day for the last 30 days: your visibility score and how many answers recommend your product. Use it to see whether your changes moved AI search engines. Needs FrontStat Pro: send your dashboard token as a Bearer token. Covers the domain on your subscription.

无需输入参数。

版本历史

1
  1. v0.1.0最新Nov 4, 2026

评分

已满足适用检查项的 90%

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
  • 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。

  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分