DataDive vs Firecrawl MCP Server
A side-by-side look at the DataDive and Firecrawl MCP Server MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose DataDive for e-commerce work as a local process; choose Firecrawl MCP Server for search & data extraction as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose DataDive when
- You need dedicated capabilities in the E-Commerce domain.
- You prefer a local stdio subprocess transport.
- You have the keys it needs:
DATADIVE_API_KEY. - You want tools like
list_niches, get_niche_keywords, list_keyword_exclusions.
Choose Firecrawl MCP Server when
- You need dedicated capabilities in the Search & Data Extraction domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: API key required.
- You have the keys it needs:
FIRECRAWL_API_KEY, HTTP_STREAMABLE_SERVER. - You want tools like
firecrawl_scrape, firecrawl_map, firecrawl_search.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | E-Commerce | Search & Data Extraction |
| Quality signal | 63/100 · Good | 90/100 · Excellent |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | API key required |
| Pricing | Not declared | Freemium |
| Required env vars | DATADIVE_API_KEY | FIRECRAWL_API_KEYHTTP_STREAMABLE_SERVER |
| Verified owner | Community listing | Verified |
| GitHub stars | 1 | 7,676 |
| Directory activity | 1 views 0 installs 0 upvotes | 15 views 0 installs 0 upvotes |
| Tools | 43 | 25 |
| Full listing | View DataDive | View Firecrawl MCP Server |
Tools & capabilities
DataDive tools 43
list_nichesUse this first when the user asks about their niches, or to find a `nicheId` for use with `get_niche_keywords`, `get_niche_competitors`, or `get_ranking_juice`. Retrieves a paginated list of Niches, newest dive first. Each Niche represents a market segment or product category being tracked. Returns nicheId, heroKeyword, nicheLabel, marketplace (com/uk/de/...), and latestResearchDate per niche, plus pagination metadata (currentPage, pageSize, total, lastPage, hasNext, hasPrev). Narrow with `searchText` (label/keyword) or `searchAsin` (a competitor ASIN) instead of scanning pages; a page holds at most 50 niches, so the full list of a large account needs several calls.get_niche_keywordsUse this when the user asks about keywords, search terms, or search volume for a niche. Retrieves the master keyword list for the specified Niche — the relevant search terms monitored for ranking and performance metrics. For each keyword, returns search volume, relevancy (numeric score or "Outlier"), and competitor ASIN organic ranks (asinRanks: { ASIN -> rank | null }), plus `origin`: `mkl` (found by the dive), `manual` (added by hand with `add_niche_keywords`), `outlier` / `residue` (moved in from those lists). Only `manual`, `outlier` and `residue` keywords can be taken out with `remove_niche_keywords`. Keywords hidden by the niche's keyword exclusions are not listed; see `list_keyword_exclusions`. Also returns the latestResearchDate.list_keyword_exclusionsUse this to see which keywords are hidden from a niche's Master Keyword List, e.g. when a keyword the user expects is missing from `get_niche_keywords`. Returns the same lists the DataDive web app shows, oldest first: `exact` — each entry hides the one keyword that matches it exactly, with that keyword's `searchVolume` (0 when the niche has no such keyword); `phrase` — each entry hides every keyword that contains the phrase, with `excludedKeywordsCount` and the total `searchVolume` of the keywords it hides (not counting ones already excluded exactly). Exclusions hide keywords wherever they come from: the dive, the Outliers and Residue lists, and hand-added ones. Change them with `add_keyword_exclusions` and `remove_keyword_exclusions`.get_niche_rootsUse this when the user wants to find the highest-impact words across a niche's keywords, asks about 'keyword roots', or wants to prioritize terms for a listing. Retrieves the keyword lexical roots for the Niche — individual words or word-combinations extracted from the Master Keyword List (e.g. 'bluetooth headphones' yields roots 'bluetooth', 'headphones', 'bluetooth headphones'). Returns `roots` and `normalizedRoots` tables, each item with root, frequency (how many keywords contain it), broadSearchVolume (summed search volume of those keywords), and broadSearchVolumeRatio (0-1, relative to the top root), plus the per-keyword breakdowns and latestResearchDate.get_niche_competitorsUse this for competitor ASINs, product titles, BSR, sales/revenue benchmarks, or niche opportunity scoring. Retrieves the list of Competitors within the specified Niche along with Niche statistics. For the Niche: keyword statistics, opportunity evaluation, benchmark median values, and overall competitor strength assessment. For each Competitor: ASIN, product title, BSR, category and full category tree, sales, revenue, ratings, reviews, price, number of variations, image URL, total Ranking Juice, and ranking data. BSR supports ranking Competitors by sales position within mentioned category. For the Ranking Juice breakdown by title, bullets and description, use `get_ranking_juice`.get_ranking_juiceUse this when the user asks 'how do I rank higher', 'what's my ranking juice', or wants listing-optimization guidance. Retrieves the Ranking Juices for each Competitor within the specified Niche. Ranking Juice is DataDive's proprietary metric identifying the key factors driving search-ranking success for each Competitor's listing. Returns currentListing and optimizedListing breakdowns (rankingJuice + per-property contributions: title, bullets, description) plus per-competitor listing scores and the latestResearchDate.list_rank_radarsUse this to find a `rankRadarId` before calling `get_rank_radar_data`. Filter by `nicheId` if the user has already identified a niche. Retrieves a paginated list of Rank Radars — keyword-rank trackers monitoring organic and sponsored positions for specific ASINs over time. Each item includes id, status (ACTIVE, PAUSED or ARCHIVED), asin, marketplace, keywordCount, title, imageUrl, and summary metrics: top10KW, top10SV, top50KW, top50SV. Supports pagination metadata (currentPage, pageSize, total, lastPage, hasNext, hasPrev); a page holds at most 50 Rank Radars, so a large account needs several calls.get_rank_radar_dataUse this to analyze keyword ranking trends over time. Requires startDate and endDate (yyyy-mm-dd), at most 90 days apart. Retrieves historical keyword ranking data for the specified Rank Radar within the date range. Without `currentPage` and `pageSize` it returns every active keyword in one result. To read one page instead — faster for large Rank Radars — pass `currentPage` and/or `pageSize` (max 100) and continue with `currentPage` + 1 while `hasNext` is true. The response carries currentPage, pageSize, total, lastPage, hasNext and hasPrev; `total` is the Rank Radar's active keyword count. Paused keywords are not included. Each keyword has id, keyword, searchVolume, relevancy, ranks (per-day { date, organicRank, sponsoredRank, impressionRank }), and `highlights` — the user tags on this keyword. Each `highlights` entry is the same object `list_rank_radar_tags` returns (id, title, color, description, startAt, endAt, type, krtId, krtKeywordId); its `id` is the `tagId` the tag-management tools take. A rank of 101 means the product was not in the top 100 results that day. For PPC metrics use `get_rank_radar_ppc_data`; for Search Query Performance use `get_rank_radar_sqp_data`. Use after `list_rank_radars` to discover a `rankRadarId`.get_rank_radar_sqp_dataUse this when the user asks how shoppers search, click, add to cart and buy for the keywords of a Rank Radar — Amazon's Search Query Performance (SQP) data, from Brand Analytics. Requires startDate and endDate (yyyy-mm-dd), at most 90 days apart; 30 days or less keeps it fast. Each keyword's metrics are aggregated over the range: searchQueryVolume and searchQueryScore; impressions, clicks, cart adds and purchases, each as the total across all sellers (`*TotalCount`), this ASIN family's count (`*AsinCount`) and its share (`*AsinShare`); click, cart-add and purchase rates; and ctr/cvr for the market (`*Total`) and for this ASIN family (`*Asin`). `numberOfDaysWithData` says how many days of the range had SQP data; metrics are null when there is none, which is normal for low-volume keywords, recent dates (Amazon publishes SQP with a delay) and sellers without Brand Analytics. Results are paged by keyword: `data` holds one page, and the response carries currentPage, pageSize, total, lastPage, hasNext and hasPrev. `total` is the Rank Radar's active keyword count; to read every keyword, call again with `currentPage` + 1 while `hasNext` is true, using `pageSize` 100 for large Rank Radars. Paused keywords are not included. Each call counts toward API usage and is rate limited (about 60 requests/minute). Use after `list_rank_radars` to discover a `rankRadarId`.get_rank_radar_ppc_dataUse this when the user asks about advertising (Sponsored Products) performance for the keywords of a Rank Radar. Requires startDate and endDate (yyyy-mm-dd), at most 90 days apart; 30 days or less keeps it fast. Each keyword's metrics are aggregated over the range: sponsoredRank (median; 101 means not in the top 100 sponsored results), impressionRank and impressionRankShare; how many exact, phrase, broad and auto campaigns target it; organicSales, ppcSales, ppcSpend, costPerClicks, clickThroughRate, conversionRate, totalClicks, totalImpressions, totalOrders and acos. Metrics are null or 0 when the seller runs no ads on a keyword. Set `includeCampaigns` for the per-campaign breakdown. Results are paged by keyword: `data` holds one page, and the response carries currentPage, pageSize, total, lastPage, hasNext and hasPrev. `total` is the Rank Radar's active keyword count; to read every keyword, call again with `currentPage` + 1 while `hasNext` is true, using `pageSize` 100 for large Rank Radars. Paused keywords are not included. Each call counts toward API usage and is rate limited (about 60 requests/minute). For the seller's campaigns as a whole, use `list_ppc_campaigns`. Use after `list_rank_radars` to discover a `rankRadarId`.list_rank_radar_tagsUse this to find a `tagId` before calling `update_rank_radar_tag`, `delete_rank_radar_tag`, `add_rank_radar_tag_search_terms` or `remove_rank_radar_tag_search_terms`. Returns the user tags ("highlights") on the specified Rank Radar, ordered by title (case-insensitive, ascending). Each row carries `id`, `title`, `color`, `description`, `startAt`, `endAt`, `createdAt`, and `keywordCount` — the number of Rank Radar keywords this tag is applied to. The system "paused" tag (the one the quota pauser writes with a reserved colour) is not listed and cannot be addressed from these tools. Supports pagination metadata (currentPage, pageSize, total, lastPage, hasNext, hasPrev); a page holds at most 50 tags.create_rank_radarUse this to start tracking organic and sponsored keyword rankings for an ASIN within a niche. ⚠️ Spends Search Term tokens (cost scales with `numberOfKeywords`) and cannot be undone — set `confirm: true` only after the user approves the cost. Not safe to retry: each call spends tokens again and creates a separate Rank Radar — if a call errors or times out, check `list_rank_radars` instead of re-calling. The first call previews the creation and may return `warnings` alongside the cost note — for example that this product family is already tracked by another Rank Radar. Show every warning `message` to the user verbatim, before asking them to confirm; do not summarise it or decide on their behalf. A warning never blocks creation. Returns the new `rankRadarId`; read its data later with `get_rank_radar_data`. Requires `asin`, `numberOfKeywords` (min 1), and a `nicheId` from `list_niches`.- +31 more on the listing page
Firecrawl MCP Server tools 25
firecrawl_scrapeRetrieve and extract content from one supplied URL through Firecrawl. Use this when the request identifies a page and needs its content or defined fields. It can return markdown, HTML, links, screenshots, branding data, a targeted answer, or JSON matching a supplied schema; JSON is useful when the requested result has defined fields, while markdown preserves readable page content. This tool operates on a known page. For a set of pages use `firecrawl_crawl`, and to discover page URLs use `firecrawl_map` or `firecrawl_search`. Options include JavaScript render delay, cache age, main-content filtering, PII redaction, and lockdown cache-only retrieval. Browser actions may change the live page when interactive actions are enabled. Firecrawl may reuse recently indexed content instead of refetching the page, and the reuse window varies by domain. Set `maxAge: 0` to force a live fetch, or a smaller `maxAge` to bound how stale reused content may be. A successful response does not by itself confirm that the state it describes is still current. Returns the selected content formats and page metadata.firecrawl_mapEnumerate URLs indexed under one website through Firecrawl without fetching each page's content. Use this when the request asks for a site's URL inventory, when several relevant pages must be located, or when the desired page URL is unknown. An optional `search` term narrows the URL list, while sitemap, subdomain, query-parameter, and result-limit options control coverage. Returns matching URLs rather than page bodies. Retrieve one page with `firecrawl_scrape`; collect content across multiple pages with `firecrawl_crawl`.firecrawl_searchSearch web, news, or image sources and return ranked results. Operators include quoted phrases, `-term`, `site:host`, `inurl:term`, `intitle:term`, and `related:host`; the set is non-exhaustive. `includeDomains` and `excludeDomains` are mutually exclusive hostname filters; categories limit results to GitHub, research, PDF, or developer sources. For a programming question, add `categories: ["developer"]`. It searches an index of GitHub issues, merged pull requests, repository READMEs, and curated documentation sites, and returns the hits in `data.developer` beside the web results. `categories: ["research"]` restricts these web results to research-affiliated websites and returns page snippets. The `firecrawl_research_*` tools are a separate surface that searches paper abstracts and full text across biomedical (PubMed, bioRxiv, medRxiv) and arXiv literature. `scrapeOptions` can attach extracted page content; pages fetched this way use a fixed reuse window and ignore `maxAge`, so use `firecrawl_scrape` when a live fetch is required. Returns source-type result groups and usage metadata. Authenticated responses can include an `id` for optional search feedback.firecrawl_crawlStart a multi-page crawl at a website URL, poll it to a terminal state, and return the final status and collected data. Scope can be bounded with include/exclude paths, depth, page limit, subdomain/external-link controls, sitemap handling, delay, and scrape options. Crawl results can be large; use conservative limits when full-site coverage is unnecessary. Webhooks and interactive scrape actions are unavailable in safe mode. Returns the crawl ID, status, and page data.firecrawl_check_crawl_statusRetrieve the current status, progress, and available results for an existing crawl ID. This only reads Firecrawl job state and does not start or modify the crawl.firecrawl_extractDeprecated compatibility entry point. Use firecrawl_scrape once per known URL with formats: ["json"] and jsonOptions containing the prompt and schema. Use firecrawl_search or firecrawl_agent before Scrape when URLs are not known.firecrawl_agentStart an asynchronous web research job from a prompt, optional seed URLs, and an optional JSON schema. Use this for a requested synthesis across multiple sources when the task can wait for asynchronous completion. The agent can search, navigate, read pages, and assemble a structured result. This call returns only a job ID, not the research result. Read the job with `firecrawl_agent_status` until it reaches `completed` or `failed`; research commonly takes several minutes. If the job cannot finish within the task's available time, `firecrawl_search` and `firecrawl_scrape` can gather evidence synchronously.firecrawl_agent_statusRetrieve progress or final results for a `firecrawl_agent` job ID. A `processing` response is non-terminal and does not contain the final research result. Check again after 15–30 seconds until the status is `completed` or `failed`; complex jobs can take several minutes. If the job cannot finish within the task's available time, use `firecrawl_search` and `firecrawl_scrape` to complete the requested output. Returns job status, progress information, and result data when completed.firecrawl_interactOpen or reuse a live browser session to navigate a page, click controls, fill fields, or run browser code. Provide either `url` or `scrapeId`, and either a natural-language `prompt` or executable `code`; code can run as Bash, Python, or Node with a bounded timeout. This acts on the live site, so actions such as form submission can create persistent external side effects. Returns execution output, stdout/stderr, exit status, and session viewing URLs.firecrawl_interact_stopStop the live interact session associated with a `scrapeId` and release its resources. Returns a success confirmation.firecrawl_parseParse one supported document into markdown, HTML, links, summary, targeted answers, or JSON matching a schema. Supported inputs include common HTML, PDF, Word, RTF, OpenDocument, and spreadsheet files; PDF parsing can be bounded with `pdfOptions.maxPages`. Local MCP reads `filePath` from the server filesystem. Hosted MCP uses two calls: first provide `filePath` to receive upload instructions, upload locally, then call again with the returned `uploadRef`; do not send both fields together. Remote web URLs belong in `firecrawl_scrape`. Set `redactPII` to request redaction of personally identifiable information in the returned content. `zeroDataRetention` requires an eligible authenticated account; omit it for anonymous keyless use. Returns upload instructions for hosted phase one or parsed document content for the final call.firecrawl_monitor_createCreate a recurring scrape, crawl, or search monitor that compares each check with its retained predecessor. The simple form accepts `page`/`pages` or `queries` plus a plain-language `goal`; the advanced `body` form controls targets, schedule, change-tracking formats, judging, retention, webhook, and notifications. In the simple form, a `goal` is required. If `queries` contains one or more non-empty values and is supplied with `page`/`pages`, `queries` create the search target and page targets are ignored. A monitor schedules future network checks and can send configured email or webhook notifications. Returns the created monitor.- +13 more on the listing page
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
DataDive
{
"mcpServers": {
"datadive": {
"command": "npx",
"args": [
"-y",
"@datadive-tools/mcp"
],
"env": {
"DATADIVE_API_KEY": "YOUR_DATADIVE_API_KEY_HERE"
}
}
}
}
Firecrawl MCP Server
{
"mcpServers": {
"firecrawl-firecrawl-mcp-server": {
"command": "npx",
"args": [
"-y",
"firecrawl-mcp"
],
"env": {
"FIRECRAWL_API_KEY": "YOUR_FIRECRAWL_API_KEY_HERE",
"HTTP_STREAMABLE_SERVER": "YOUR_HTTP_STREAMABLE_SERVER_HERE"
}
}
}
}
Frequently asked questions
DataDive is categorized under E-Commerce and uses a local stdio subprocess. Firecrawl MCP Server belongs to Search & Data Extraction and uses a local stdio subprocess. Pick DataDive for e-commerce work and Firecrawl MCP Server for search & data extraction.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
DataDive has no declared pricing — check the project's own site. Firecrawl MCP Server is listed as freemium — a free tier with paid plans. Auth: api key required. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add datadive and firecrawl-firecrawl-mcp-server as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, DataDive has a quality signal of 63/100 (Good) with 1 views, 0 installs and 1 GitHub stars. Firecrawl MCP Server has 90/100 (Excellent) with 15 views, 0 installs and 7,676 GitHub stars.
