DeepScout

Name: DeepScout
Author: deepscout-ai

作者：deepscout-ai版本 1.0.1i★ –i在云端运行

注册名称ai.deepscout/deepscout

安装

概览

作者提供的说明（英文原文）

Scrape any e-shop and match products across shops without EAN. API & MCP for AI agents.

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。

用户评价i暂无评价评价功能将在后续阶段与账户功能一起开放
我们的基础检查i1 项中通过 1 项依据公开信息检查；尚未扫描代码
使用情况i尚未统计★ –

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: 在云端运行
传输方式: Streamable HTTP
分类: 网页与浏览器

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
在作者的服务器上运行：你向它提出的内容会经过他们的服务器。
注册中心没有列出需要填写的密钥。

你需要

在云端运行无需安装任何东西，通过互联网连接

你用的是哪个应用？

ClaudeClaude CodeCursorVS CodeChatGPT

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 …”。

适用于网页版、桌面版和手机版 Claude：

打开 Settings → Connectors
点击 Add custom connector
粘贴下面的地址，然后点击 Add
如果要求登录，请登录作者的服务

https://mcp.deepscout.ai/mcp

在终端中运行这条命令

claude mcp add --transport http deepscout https://mcp.deepscout.ai/mcp

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": {
    "deepscout": {
      "url": "https://mcp.deepscout.ai/mcp"
    }
  }
}

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": {
    "deepscout": {
      "type": "http",
      "url": "https://mcp.deepscout.ai/mcp"
    }
  }
}

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。

ChatGPT 只能连接互联网上的服务器：

打开网页版 ChatGPT → Settings → Connectors (Apps)
点击 Create 或 Add（部分套餐需要先在 Advanced 中开启 Developer mode）
粘贴下面的地址，起个名字，然后保存
如果要求登录，请登录作者的服务

https://mcp.deepscout.ai/mcp

菜单名称可能因套餐和版本不同而略有差异。

你的选择通过 Cookie 保存在这台设备上，无需账户。

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

我们还没有读取这个服务器的工具列表；我们会轮流检查各个端点。

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6日

✓ 通过
作者与仓库一致
注册名称已通过域名 deepscout.ai 验证（注册中心会核实域名所有权）
… 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
… 尚未检查
端点有响应
尚未检查；我们会轮流检查各个端点
… 尚未检查
使用 OAuth 登录
尚未检查；我们会轮流检查各个端点
… 尚未检查
工具描述中没有隐藏指令
尚未检查；我们会在检查端点时读取工具列表

与“网页与浏览器”中的其他服务器比较i

星标数多于此分类中其他 876 个服务器的 0%
发布到注册中心的时间比此分类中其他 876 个服务器的 75% 更新
基础检查结果等于或优于此分类中其他 876 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

DeepScout 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？

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？

它在作者的云端运行。通过互联网连接，无需安装，但你发送的内容会经过作者的服务器。

它还在维护吗？

GitHub 仓库最后更新于–，最新版本（1.0.1）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，所以接受远程 MCP 服务器的应用也可以使用，例如开启开发者模式的 ChatGPT。

有什么可以替代它？

同一分类中有：Browser Use, Chrome DevTools MCP, MCP Server Browser

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

Browser Use

作者：browser-use

Browser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data.

电脑或云端★ 120,087MIT16天前更新

安装

Chrome DevTools MCP

作者：ChromeDevTools

MCP server for Chrome DevTools

在你的电脑上运行★ 54,821Apache-2.015天前更新

安装

MCP Server Browser

作者：bytedance

MCP server for browser use access

在你的电脑上运行★ 39,550Apache-2.014个月前更新

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。

DeepScout MCP server

Scrape product catalogs from any e-shop and match the same products across shops, with no EAN or GTIN needed. Works from Claude, Claude Code, Cursor, Codex, VS Code and any other MCP client.

DeepScout (deepscout.ai) hosts the server, so you install nothing. You write what you want in plain language, and the agent calls the DeepScout API for you.

https://mcp.deepscout.ai/mcp

What you can do with it

Scrape an e-shop. Add a website, check the free sample, then scrape the full catalog or only a list of product URLs. DeepScout handles browser rendering, anti-bot protection, proxies and pagination.
Match products across shops. Find the same product in your shop and in your competitors' shops, by name, parameters and images. Product matching works when the shops share no EAN, GTIN or SKU.
Use the data. Download the exports and let the agent compare your prices with the market or find the products your competitors sell and you do not.

Setup

The server uses the Streamable HTTP transport and OAuth 2.1 sign-in. Add the server URL to your client and start the sign-in. The client opens the DeepScout console. Sign in with Google or GitHub; your first sign-in creates your account.

Claude Code

claude mcp add --transport http deepscout https://mcp.deepscout.ai/mcp

Start a session, run /mcp, select deepscout, then Authenticate.

Claude (claude.ai and Claude Desktop)

Open Settings → Connectors and click Add custom connector. Enter the name DeepScout and the server URL, then click Connect.

Cursor

Add to ~/.cursor/mcp.json or .cursor/mcp.json in your project:

"mcpServers": { "deepscout": { "url": "https://mcp.deepscout.ai/mcp" } } }

Open Cursor Settings → MCP and click Connect next to deepscout.

Codex

codex mcp add deepscout --url https://mcp.deepscout.ai/mcp

If Codex does not open the sign-in, run codex mcp login deepscout.

VS Code

Add to .vscode/mcp.json in your workspace:

"servers": { "deepscout": { "type": "http", "url": "https://mcp.deepscout.ai/mcp" } } }

Click Start above the server in the file.

Clients with local (stdio) servers only

"mcpServers": { "deepscout": { "command": "npx", "args": ["-y", "mcp-remote", "https://mcp.deepscout.ai/mcp"] } } }

mcp-remote needs Node.js 18 or later.

With an API key instead of the sign-in

Create a key in the console under Settings → API keys and send it in the Authorization header:

claude mcp add --transport http deepscout https://mcp.deepscout.ai/mcp \

--header "Authorization: Bearer $SCOUT_API_KEY"

A key for one project keeps the agent inside that project.

Tools

Tool	What it does
`scout_list_projects`	Lists your projects and the customer that pays for each one.
`scout_create_project`	Creates a project, e.g. for another client or market.
`scout_list_websites`	Lists the websites of a project with their current job and full scrape estimate.
`scout_analyze_website`	Adds a website to a project. The setup job analyzes it and scrapes free sample products.
`scout_get_sample`	Gives a temporary URL of the sample products of a website.
`scout_scrape_website`	Creates a scraping job for the full catalog or for a list of product URLs.
`scout_get_url_results`	Gives the result of each URL of a URL scrape.
`scout_match_websites`	Creates a matching job, or the free matching sample of the project.
`scout_list_jobs`	Lists the newest jobs of a kind in a project.
`scout_get_job`	Reads a setup, scraping or matching job: status, progress, estimate and charge.
`scout_approve_job`	Approves a scraping or matching job. This charges your credit.
`scout_cancel_job`	Cancels a job that waits for approval. Nothing is charged.
`scout_list_exports`	Lists the export files of a project.
`scout_get_export`	Gives a temporary URL of one export file.
`scout_get_balance`	Reads your credit: total, held and spendable.

Only scout_approve_job charges your credit. The server tells the agent to show you the price and wait for your answer first. Keep your client's confirmation prompt on for this tool. The read-only tools (scout_list_*, scout_get_*) carry the readOnlyHint annotation.

Example prompts

Change the values in brackets.

Add a competitor and check the sample

Add [https://www.example-shop.com] to my DeepScout project [Default project]. The market is [DE] and the currency is [EUR]. Wait until the setup job is complete. Then download the sample and tell me which fields are often empty or look wrong. Do not start a paid scrape.

Match my products with competitors

In my DeepScout project [Default project], [my-shop.com] is my website and [competitor-a.com, competitor-b.com] are my competitors. Run the free matching sample first. When it is complete, show me 10 matched pairs from the export. Then create the full matching, show me the price and wait for my approval.

Compare my prices with the market

Get the matches export of my DeepScout project [Default project] and the product export of each website in it. For each of my products that has at least one competitor, compare my price with the lowest competitor price. List the 20 products with the largest difference in percent.

Find gaps in my assortment

Get the matches export of my DeepScout project [Default project]. My website is [my-shop.com]. List the products that two or more competitors sell and my website does not, with the lowest price. Sort them by the number of competitors.

Pricing

Usage-based, paid from prepaid credit. The same prices as the API:

Website analysis and sample data: 10 shops a month free, then €0.50 per analysis
Scraping: from €0.40 per 1,000 products
Matching: €7 per 1,000 products, with a free matching sample first

See deepscout.ai/dev for details.

Notes

Jobs run at a rate that each e-shop accepts. A scrape of 100,000 products can take a day. You can close the conversation and ask about the job later.
The agent cannot top up credit. Top up in the console.