Agent Signal vs DataDive
A side-by-side look at the Agent Signal and DataDive MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Agent Signal for e-commerce work as a local process; choose DataDive for e-commerce as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Agent Signal when
- You need dedicated capabilities in the E-Commerce domain.
- You prefer a local stdio subprocess transport.
- You have the keys it needs:
DATABASE_URL. - You want tools like
agent_signal_status, smart_shopping_session, evaluate_and_compare.
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.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | E-Commerce | E-Commerce |
| Quality signal | 41/100 · Fair | 63/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | Not declared |
| Pricing | Not declared | Not declared |
| Required env vars | DATABASE_URL | DATADIVE_API_KEY |
| Verified owner | Community listing | Community listing |
| GitHub stars | 0 | 1 |
| Directory activity | 4 views 0 installs 0 upvotes | 1 views 0 installs 0 upvotes |
| Tools | 30 | 43 |
| Full listing | View Agent Signal | View DataDive |
Tools & capabilities
Agent Signal tools 30
agent_signal_statusGet an overview of the AgentSignal collective intelligence network. Call this with NO arguments to see what categories have data, trending products, and how to use agent-signal tools. Good first call if you're unsure whether agent-signal has data relevant to the user's request.smart_shopping_sessionCALL THIS FIRST when the user wants to buy, find, compare, or get recommendations for any product. Logs the shopping intent and instantly returns what other AI agents chose for similar requests — top products, deciding factors, price data, and outcomes. One call replaces hours of research. Returns a session_id needed for follow-up tools like evaluate_and_compare.evaluate_and_compareLog a product evaluation AND instantly get intelligence about it in one call. Call this for EACH product you consider during a shopping task. Returns how other agents rated this product, whether the price is a deal or overpriced, top rejection reasons, and competitive alternatives. Requires a session_id from smart_shopping_session.get_todays_dealsSee the best deals spotted by AI agents right now. Call this with NO arguments when the user asks 'any good deals?', 'what should I buy?', or wants shopping inspiration. Returns products currently priced 10%+ below their average, ranked by savings. Great for proactive recommendations — even without a specific shopping request.search_productsSearch for products across the entire agent network by name or keyword. Call this when the user mentions a product name, brand, or type and you want to find what other agents know about it. Returns selection rates, prices, and merchants. Example: search_products(query='sony headphones') or search_products(query='running shoes', category='footwear/running')get_trending_productsSee what products are trending up or down right now. Call this when the user asks what's popular, what's hot, or wants general shopping inspiration WITHOUT a specific product in mind. No category required — omit for all trends. Returns rising and falling products with selection rate changes.get_category_recommendationsGet intelligence about what works best in a product category. Call this when the user mentions a product type (headphones, running shoes, laptops, etc.) even casually. Returns top-performing products, what decision factors matter most, common requirements, and average budgets from other AI agents' sessions.get_budget_productsFind the best products within a specific budget for a category. Call this when the user says 'under $X' or has a clear budget constraint. ranked by selection count. Includes which merchants offer it under budget.get_constraint_matchDecision shortcut: find what products worked for agents with your EXACT constraints. Matches on specific requirements (e.g. 'wide fit + cushioned + under $150') and returns what those agents selected, why, and where to buy. Also returns broader recommendations from sessions with overlapping constraints. Use this to skip the search when a proven answer already exists.get_price_historySee a product's price history over time from all agent observations. Call this when the user asks 'is now a good time to buy?' or 'has this been cheaper?'. Returns daily price trends, all-time low/high, and price breakdown by merchant.detect_dealIs this price good? Compare any product's current price against historical data from all agents. Call this whenever you see a price and want to know if it's a deal or overpriced. Returns a verdict (best_price_ever, great_deal, good_deal, fair_price, above_average), savings vs average, and which merchants typically have the best prices.get_product_intelligenceShould I recommend this product? Get crowdsourced intelligence from other AI agents. Call this when you're considering a specific product and want to know its track record. Returns selection rate, rejection reasons, which competitors beat it and why, price ranges, and purchase outcomes.- +18 more on the listing page
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
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.
Agent Signal
{
"mcpServers": {
"agent-signal": {
"command": "npx",
"args": [
"-y",
"agent-signal"
],
"env": {
"DATABASE_URL": "YOUR_DATABASE_URL_HERE"
}
}
}
}
DataDive
{
"mcpServers": {
"datadive": {
"command": "npx",
"args": [
"-y",
"@datadive-tools/mcp"
],
"env": {
"DATADIVE_API_KEY": "YOUR_DATADIVE_API_KEY_HERE"
}
}
}
}
Frequently asked questions
Agent Signal is categorized under E-Commerce and uses a local stdio subprocess. DataDive belongs to E-Commerce and uses a local stdio subprocess. Pick Agent Signal for e-commerce work and DataDive for e-commerce.
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.
Agent Signal has no declared pricing — check the project's own site. DataDive has no declared pricing — check the project's own site. 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 agent-signal and datadive as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Agent Signal has a quality signal of 41/100 (Fair) with 4 views, 0 installs and 0 GitHub stars. DataDive has 63/100 (Good) with 1 views, 0 installs and 1 GitHub stars.