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。使用 Google 登录即可撰写评价。原型 · 每 30 分钟更新
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

DataDive

作者:Data-Dive-Tools版本 1.112.0i★ 1i在云端运行
注册名称tools.datadive/datadive

安装方法

What it does

Amazon niche, keyword, competitor and Rank Radar research from your DataDive account.

  • Connects 在云端运行
  • Account or key Sign in to the service when you connect (OAuth)
  • Category 网店与支付

安装

选择你使用的 AI 应用,然后复制设置。

通过 4/4 项检查 · 你的提问会经过开发者的服务器(mcp.datadive.tools) · ✓ 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

  1. 打开 Claude 的 Connectors 页面

    CustomizeConnectors

    CustomizeConnectors1Add2https://…3Add4
  2. 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DataDive
    Remote MCP server URL · 地址https://mcp.datadive.tools/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

  3. 在聊天中开启

    +ConnectorsDataDive

  4. 试一试

    用 DataDive 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 DataDive,或回答中出现 DataDive 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

  1. 在网页版 ChatGPT 打开添加 MCP 的页面

    Plugins+Add custom MCP server

    ChatGPTPlugins1+2https://…3Create4
  2. 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DataDive
    Connection · 地址https://mcp.datadive.tools/mcp
  3. 在聊天中选择 DataDive

    开启新聊天,输入前先从插件列表中选择 DataDive

  4. 试一试

    用 DataDive 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 DataDive,或回答中出现 DataDive 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

  1. 打开终端

    Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell

  2. 粘贴这条命令并按 Enter

    claude mcp add --transport http --scope user datadive https://mcp.datadive.tools/mcp
  3. 在 Claude Code 中输入 /mcp

    应能看到 DataDive 在列表中并显示已连接

  4. 试一试

    用 DataDive 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 DataDive,或回答中出现 DataDive 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

  1. 点击这个按钮打开 Cursor

    在 Cursor 中打开

    Cursor 会请你确认安装,点击 Install

  2. 在 Cursor 中以 Agent 模式打开 AI 聊天

  3. 试一试

    用 DataDive 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 DataDive,或回答中出现 DataDive 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

  1. 点击这个按钮打开 VS Code

    在 VS Code 中打开

    VS Code 会请你确认安装,点击 Install

  2. 在 VS Code 中以 Agent 模式打开 AI 聊天

  3. 试一试

    用 DataDive 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 DataDive,或回答中出现 DataDive 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

查看所有支持 MCP 的应用 →

通过网页连接的应用使用的地址

地址https://mcp.datadive.tools/mcp

JSON 设置在下方“开发者专用”中

卡住了?问问正在用 DataDive 的人💬 讨论 →
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 datadive https://mcp.datadive.tools/mcp

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "datadive": {
      "url": "https://mcp.datadive.tools/mcp"
    }
  }
}

VS Code (mcp.json)

{
  "servers": {
    "datadive": {
      "type": "http",
      "url": "https://mcp.datadive.tools/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

每周下载量i
不在 npm/PyPI 上
已验证域名
✓ datadive.tools
连接方式
在云端运行
传输方式
streamable-http
最新版本i
1.112.0
发布到注册中心i
2026年11月6日
代码最后更新i
2026年11月5日
作者
Data-Dive-Tools
注册状态
活跃

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

全部应用及其优缺点 →

它能做什么

服务器要求先登录,才会列出它的工具。

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15日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过域名 datadive.tools 验证(注册中心会核实域名所有权)

  • ✓ 通过

    仍在维护

    代码最后更新于10天前

  • – 不适用

    有许可证

    不适用:由 datadive.tools 的所有者自己运行的云端服务器,你不会运行仓库里的代码

  • ✓ 通过

    端点有响应

    在 276 毫秒内响应(HTTP 401)

  • ✓ 通过

    使用 OAuth 登录

    声明支持 OAuth 登录,你的 AI 应用可以带你去登录

  • … 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

我们检查什么 → · JSON

作者:申请重新检查或报告信息错误

讨论

提问、分享技巧或报告无法使用。按“有帮助”数量排序。

还没有帖子,欢迎第一个提问或分享。

此处内容由用户撰写,不代表 PopNx 团队。

登录后发帖

用户评价

还没有评价

登录后写评价

与“网店与支付”中的其他服务器比较i

  • 星标数多于此分类中其他 2813 个服务器的 90%
  • 发布到注册中心的时间比此分类中其他 2813 个服务器的 77% 更新
  • 基础检查结果等于或优于此分类中其他 2813 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

DataDive 安全吗?

它在 4 项适用的基础检查中通过了 4 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10天前,最新版本(1.112.0)于9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:Stripe MCP, flightclaw, Trade It, Vaaya, Marketplace Ad Pros: Amazon Ads & Seller Central

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

Stripe MCP

MCP server integrating with Stripe - tools for customers, products, payments, and more.

作者:stripe广泛使用★ 206113个月前更新

在云端运行✓ 服务方 · stripe.com

flightclaw

Search ~300 airlines and book flights with a checkout link. OAuth sign-in by email code.

作者:flightclaw正在增长★ 852个月前更新

在云端运行✓ 服务方 · flightclaw.com

Trade It

Connect brokerage accounts to AI assistants: holdings, orders, asset lookup, and approved trading.

作者:trade-it-inc起步阶段★ 6230天前更新

在云端运行✓ 服务方 · tradeit.app

Vaaya

Paid APIs and tokenized shares for agents. Prepaid funding, including authorized Instinct checkout.

作者:vaaya-ai起步阶段↓ 123/周★ 442个月前更新

电脑或云端✓ 服务方 · vaaya.ai

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。

@datadive-tools/mcp

An MCP server that lets Claude (or any MCP-compatible client) query your DataDive niches, keywords, competitors, and Rank Radar data using your existing API key.

Runs locally on your machine over stdio. Your API key never leaves your machine except as the x-api-key header on requests to api.datadive.tools.

What you can ask

  • "List my DataDive niches in marketplace com."
  • "What's the master keyword list for niche z515cGOFg3?"
  • "Who are the top competitors in niche X and what are their sales?"
  • "What's my ranking juice for niche X — where can I improve?"
  • "Show me my rank radars."
  • "Plot the organic ranking trend for rank radar Y from 2024-03-01 to 2024-04-01."
  • "Run a niche dive on ASIN B08N5WRWNW in the US marketplace with 5 competitors."
  • "Refresh niche X with today's data, same competitors."
  • "Re-dive niche X with 12 competitors but keep B08N5WRWNW in the set."
  • "Is my dive done yet?"
  • "Start a rank radar tracking 10 keywords for ASIN B08N5WRWNW in niche X."
  • "Which Amazon seller accounts are connected?"
  • "Search my catalog for active 'widget' products in the US."
  • "What price or content changes happened on my listings last week?"

1. Get a DataDive API key

  1. Sign in at https://2.datadive.tools.
  2. Go to Settings → API Key (/api-key).
  3. Click Generate API Key. Copy the value — you'll paste it into your MCP client config below.

Requires the Billing Manager or Owner role and the **Standard plan

or higher**. Contact your org admin if you can't see the page.

2. Add it to your MCP client

Claude Desktop

Edit your config file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json

Add the datadive entry under mcpServers:

{

"mcpServers": { "datadive": { "command": "npx", "args": ["-y", "@datadive-tools/mcp"], "env": { "DATADIVE_API_KEY": "YOUR_API_KEY" } } } }

Restart Claude Desktop. You should see datadive in the tools menu.

Claude Code
claude mcp add datadive -- npx -y @datadive-tools/mcp

Then add the env var via:

claude mcp add datadive --env DATADIVE_API_KEY=YOUR_API_KEY -- npx -y @datadive-tools/mcp

Or edit .mcp.json in your project / ~/.claude/mcp.json globally with the same JSON shape as above.

Cursor

Settings → MCP → Add new MCP server and paste the same JSON shape:

{

"datadive": { "command": "npx", "args": ["-y", "@datadive-tools/mcp"], "env": { "DATADIVE_API_KEY": "YOUR_API_KEY" } } }

3. Verify

Ask Claude: "List my DataDive niches."

You should see a tool call to list_niches and a JSON response with your niches, plus pagination metadata. If you don't, see Troubleshooting below.

Available tools

ToolDescription
list_nichesPaginated list of your niches. Discovery step — returns nicheIds for the niche-scoped tools below.
list_nichesPaginated list of your niches. Discovery step — returns nicheIds for the niche-scoped tools below. Filter by searchText, searchAsin, spaces or labels; each niche lists the ids of its spaces and labels.
list_spacesYour Spaces as a tree (id, name, path, children). A connected member sees only the Spaces they have rights on. Ids feed add_niche_spaces and the spaces filters.
list_labelsYour labels as a tree. Ids feed add_niche_labels and the labels filters.
list_fast_keywordsPaginated list of your organization's Fast Keywords runs (fastKeywordsId, ASIN, status, keyword count, search volume). Filter by search or marketplace.
get_fast_keywordsOne Fast Keywords result: product, keyword roots and the top 10 competitors. Poll it until status is success.
get_fast_keywords_keywordsThe keywords of a finished Fast Keywords run: search volume, organic and sponsored rank, highest volume first. Paged (up to 100).
run_fast_keywordsSpends 1 dive token. Finds a product's keywords from just its ASIN. Async — poll get_fast_keywords. Previews the cost first and requires confirm: true.
refresh_fast_keywordsSpends 1 dive token. Re-runs a Fast Keywords result; allowed once every 24 hours. Requires confirm: true.
get_niche_keywordsMaster keyword list for a niche: search volume, relevancy, competitor ASIN ranks, suggested bid.
get_niche_outlier_keywordsA niche's Outliers, paginated: high search volume keywords only a few competitors rank for.
get_niche_residue_keywordsA niche's Residue, paginated: keywords in neither the Master Keyword List nor the Outliers.
get_niche_rootsKeyword lexical roots for a niche — high-impact words with frequency and broad search volume.
get_niche_competitorsCompetitor ASINs, titles, BSR, category and niche statistics (sales, revenue, ratings, opportunity score).
get_ranking_juiceDataDive proprietary ranking-juice metric per competitor (current vs optimized listing).
list_rank_radarsPaginated list of rank radars. Filter by nicheId, searchText, spaces, labels (matched through the niche) or status (ACTIVE by default, plus PAUSED, ARCHIVED, ALL).
get_rank_radar_dataHistorical keyword rankings for a rank radar within a startDate/endDate range (max 90 days). Returns every active keyword by default; pass currentPage/pageSize (up to 100) to read one page at a time.
get_rank_radar_sqp_dataAmazon Search Query Performance per Rank Radar keyword: search volume, impressions, clicks, cart adds, purchases — market total vs this ASIN family. Same date range and paging as get_rank_radar_data.
get_rank_radar_ppc_dataSponsored Products metrics per Rank Radar keyword: sponsored rank, spend, sales, ACOS, CPC, match types; optional per-campaign breakdown. Same date range and paging as get_rank_radar_data.
create_niche_diveSpends dive tokens. Starts new niche research from a seed ASIN. Async — returns a diveId to poll with get_dive_status. Pass fastKeywordsRequestId (from run_fast_keywords) to link it to a Fast Keywords run. Requires confirm: true.
create_niche_dive_from_competitors_listSpends dive tokens. Starts niche research from your own list of 2–200 competitor ASINs, with no automatic discovery. Async — returns a diveId to poll with get_dive_status. Requires confirm: true.
redive_nicheSpends dive tokens. Refreshes an existing niche with current data — either the same competitors or a newly discovered set. Async — returns a diveId to poll with get_dive_status. Requires confirm: true.
add_niche_keywordsAdds keywords to a niche's Master Keyword List (1–100 per call). Free on a niche dived in the last 24 hours. On an older niche it re-dives the niche and spends dive tokens — then it asks for confirm: true first.
remove_niche_keywordsTakes keywords back out of a niche's Master Keyword List: hand-added ones are deleted, ones from Outliers/Residue go back there, dive-found ones stay. Free.
list_keyword_exclusionsThe keywords a niche hides from its Master Keyword List: exact entries with their search volume, phrase entries with how many keywords and how much search volume they hide.
add_keyword_exclusionsHides keywords from a niche's Master Keyword List — exact (one keyword) or phrase (every keyword containing it), 1–100 entries per call. Free; undone by remove_keyword_exclusions.
remove_keyword_exclusionsRemoves exact or phrase exclusions so the keywords they hid show again. Free.
add_niche_spaces / remove_niche_spacesPuts a niche in, or takes it out of, 1–100 Spaces (spaceIds from list_spaces). Free, no confirm. Needs Manage access to the niche, as in the web app; a Space you only have view rights on is refused. One unknown or refused id fails the whole call and nothing changes.
add_niche_labels / remove_niche_labelsSame for labels (labelIds from list_labels). Needs Manage access to the niche.
get_dive_statusPoll a dive started by create_niche_dive or redive_niche: in_progress, success (carries the nicheId), or error.
create_rank_radarSpends Search Term tokens. Starts tracking keyword rankings for an ASIN in a niche. Returns a rankRadarId. Requires confirm: true.
add_rank_radar_search_termsStarts tracking extra keywords on an existing rank radar. Takes one Daily Tracked Keywords slot per new keyword; reversible with pause_rank_radar_search_terms.
pause_rank_radar_search_termsPauses individual keywords of a rank radar, keeping their history and freeing their tracking slots. Takes keyword ids from get_rank_radar_data.
resume_rank_radar_search_termsRestarts tracking on paused keywords of a rank radar. Takes back one tracking slot each.
pause_rank_radarPauses a whole rank radar (what the API calls archiving — listed under status: PAUSED, not ARCHIVED). Tracking stops, the history is kept, and the tracking slots are freed. Reversible with resume_rank_radar.
resume_rank_radarReactivates a paused rank radar, restoring as many keywords as the remaining quota allows (most relevant first).
delete_rank_radarDestroys ranking history. Deletes a rank radar permanently (listed under status: ARCHIVED) and frees its tracking slots. Requires confirm: true — prefer pause_rank_radar if the data may be wanted later.
delete_nicheDestroys niche data. Deletes a niche with its keywords, competitors and dive history; spent dive tokens are not refunded. Blocked while a rank radar uses the niche. Requires confirm: true.
generate_listing_copySpends an AI Copywriter prompt. Drafts an optimised title, bullets and description from a niche's keyword research. Nothing is published to Amazon. Async — returns a generationId. Requires confirm: true.
get_listing_copy_generation_statusPoll a draft started by generate_listing_copy: generating, complete (carries the generated copy), or failed. Free to poll.
list_seller_profilesPaginated list of connected Amazon seller accounts. Discovery step — returns the sellerId + marketplace the seller-scoped tools below (and the alert tools) need.
get_seller_catalogPaginated catalog of a seller's own ASINs. Filter by search, brand, and status (Active by default).
get_seller_listing_changesPaginated price/content/image changes on a seller's listings. Filter by types, asin, brand, search, and a date range; optionally include ranking/conversion correlation.
list_ppc_campaignsSponsored Products campaigns of a seller account with window totals and a per-placement breakdown. Filter by asin / parentAsin, state, search; sort by any metric. Window up to 90 days (default 30).
get_asin_inventory_distributionInventory metrics for an ASIN (stock, days of stock, low-inventory state, LILF and LTSF fees, aged units) and its per-fulfillment-center sellable inventory. Requires sellerId from list_seller_profiles or your Connections page.
list_indexing_issue_alertsPaginated list of indexing-issue alerts — ASINs no longer indexed for their tracked keywords. Filter by sellerId, marketplace, status, or updatedSince.
list_blind_spend_alertsPaginated list of blind-spend alerts — ad spend on search terms with little or no sales, with per-term spend/clicks/CVR. Same filters as above.
get_quotaCurrent quota usage and capacity per billable feature, plus the next refresh date. No arguments.
list_usagePaginated billable usage logs (token-consumption events). Filter by type, search (user), and startDate/endDate.

Al

只显示了开头部分;其余内容请在仓库中阅读