DataDive

Name: DataDive
Author: Data-Dive-Tools

作者：Data-Dive-Tools版本 1.88.0i★ –i在云端运行

注册名称tools.datadive/datadive

安装

概览

作者提供的说明（英文原文）

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

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: 搜索与 AI 记忆

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.datadive.tools/mcp

在终端中运行这条命令

claude mcp add --transport http datadive https://mcp.datadive.tools/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": {
    "datadive": {
      "url": "https://mcp.datadive.tools/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": {
    "datadive": {
      "type": "http",
      "url": "https://mcp.datadive.tools/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.datadive.tools/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 datadive.tools 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“搜索与 AI 记忆”中的其他服务器比较i

星标数多于此分类中其他 7234 个服务器的 0%
发布到注册中心的时间比此分类中其他 7234 个服务器的 76% 更新
基础检查结果等于或优于此分类中其他 7234 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 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（1.88.0）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：Context7, Codebase Memory, Exa

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

Context7

作者：upstash

Up-to-date docs for AI agents

电脑或云端★ 64,224MIT3天前更新

安装

Codebase Memory

作者：DeusData

Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.

在你的电脑上运行★ 48,148MIT20天前更新

安装

Exa

作者：exa-labs

Connect AI agents to Exa for web search, content fetching, and multi-step research.

在云端运行★ 5,213MIT44天前更新

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。

@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

Sign in at https://2.datadive.tools.
Go to Settings → API Key (/api-key).
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

Tool	Description
`list_niches`	Paginated list of your niches. Discovery step — returns `nicheId`s for the niche-scoped tools below.
`list_niches`	Paginated list of your niches. Discovery step — returns `nicheId`s for the niche-scoped tools below. Filter by `searchText`, `searchAsin`, `spaces` or `labels`; each niche lists the ids of its `spaces` and `labels`.
`list_spaces`	Your 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_labels`	Your labels as a tree. Ids feed `add_niche_labels` and the `labels` filters.
`list_fast_keywords`	Paginated list of your organization's Fast Keywords runs (`fastKeywordsId`, ASIN, status, keyword count, search volume). Filter by `search` or `marketplace`.
`get_fast_keywords`	One Fast Keywords result: product, keyword roots and the top 10 competitors. Poll it until `status` is `success`.
`get_fast_keywords_keywords`	The keywords of a finished Fast Keywords run: search volume, organic and sponsored rank, highest volume first. Paged (up to 100).
`run_fast_keywords`	Spends 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_keywords`	Spends 1 dive token. Re-runs a Fast Keywords result; allowed once every 24 hours. Requires `confirm: true`.
`get_niche_keywords`	Master keyword list for a niche: search volume, relevancy, competitor ASIN ranks, suggested bid.
`get_niche_outlier_keywords`	A niche's Outliers, paginated: high search volume keywords only a few competitors rank for.
`get_niche_residue_keywords`	A niche's Residue, paginated: keywords in neither the Master Keyword List nor the Outliers.
`get_niche_roots`	Keyword lexical roots for a niche — high-impact words with frequency and broad search volume.
`get_niche_competitors`	Competitor ASINs, titles, BSR, category and niche statistics (sales, revenue, ratings, opportunity score).
`get_ranking_juice`	DataDive proprietary ranking-juice metric per competitor (current vs optimized listing).
`list_rank_radars`	Paginated 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_data`	Historical 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_data`	Amazon 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_data`	Sponsored 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_dive`	Spends 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_list`	Spends 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_niche`	Spends 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_keywords`	Adds 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_keywords`	Takes 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_exclusions`	The 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_exclusions`	Hides 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_exclusions`	Removes exact or phrase exclusions so the keywords they hid show again. Free.
`add_niche_spaces` / `remove_niche_spaces`	Puts 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_labels`	Same for labels (`labelIds` from `list_labels`). Needs Manage access to the niche.
`get_dive_status`	Poll a dive started by `create_niche_dive` or `redive_niche`: `in_progress`, `success` (carries the `nicheId`), or `error`.
`create_rank_radar`	Spends Search Term tokens. Starts tracking keyword rankings for an ASIN in a niche. Returns a `rankRadarId`. Requires `confirm: true`.
`add_rank_radar_search_terms`	Starts 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_terms`	Pauses 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_terms`	Restarts tracking on paused keywords of a rank radar. Takes back one tracking slot each.
`pause_rank_radar`	Pauses 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_radar`	Reactivates a paused rank radar, restoring as many keywords as the remaining quota allows (most relevant first).
`delete_rank_radar`	Destroys 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_niche`	Destroys 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_copy`	Spends 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_status`	Poll a draft started by `generate_listing_copy`: `generating`, `complete` (carries the generated copy), or `failed`. Free to poll.
`list_seller_profiles`	Paginated list of connected Amazon seller accounts. Discovery step — returns the `sellerId` + `marketplace` the seller-scoped tools below (and the alert tools) need.
`get_seller_catalog`	Paginated catalog of a seller's own ASINs. Filter by `search`, `brand`, and `status` (Active by default).
`get_seller_listing_changes`	Paginated 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_campaigns`	Sponsored 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_distribution`	Inventory 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_alerts`	Paginated list of indexing-issue alerts — ASINs no longer indexed for their tracked keywords. Filter by `sellerId`, `marketplace`, `status`, or `updatedSince`.
`list_blind_spend_alerts`	Paginated 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_quota`	Current quota usage and capacity per billable feature, plus the next refresh date. No arguments.
`list_usage`	Paginated billable usage logs (token-consumption events). Filter by `type`, `search` (user), and `startDate`/`endDate`.

只显示了开头部分；其余内容请在仓库中阅读