VERTICAL(ecommerce): dynamic pricing strategy + rules. input=catalog+goal. B2B: online stores optimize margin/volume. [x402: 15.0 USDC on Base, pay-per-use]
ConnectorNo auth
751,414 tools. Updated 2026-11-06 14:41
"Ecommerce" matching MCP tools:
- Submit the buyer's **product/feature request** to the Kifly team. Use this when the buyer wishes Kifly *itself* did something it doesn't — a missing capability, a rough flow, an idea to improve the platform. **This is NOT `submit_feedback`** (that's for reporting a broken/confusing API response you hit). Requires the buyer's `kfb_live_` token — only registered buyers can file requests. Help the buyer articulate a real problem: ask OPEN, non-leading questions ('what were you trying to do? what got in the way? how do you handle it today?') — never 'would feature X help?'. Pre-fill the fields from the conversation and ask only for the gaps; keep it short. Separate the `problem` (the pain) from any `proposed_solution` (the fix). Name and email are taken from the buyer profile automatically — do not ask for them. Returns 202: it's logged for review. **Do NOT promise the user anything will be built** — just confirm it was recorded.ConnectorNo auth
- Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks. Call with NO args for a `trending_scan` of the top ~200 markets by weekly volume; pass `event` for the strongest per-event partition_check, or `topic` for a themed cross-event scan. `event` (recommended for a specific market): pass a Polymarket event slug like "fed-decision-may-2026" or "when-will-bitcoin-hit-150k"; walks child markets, checks date-axis / threshold-axis ordering AND computes the partition_check (sum of YES prices across mutually-exclusive legs — should ≈1; deviations >3pp emit a BUY/SELL EVERY LEG signal). `topic` (for cross-event scanning): pass a seed question like "Strait of Hormuz traffic returns to normal" or "Fed rate decision"; searches related events across the platform, flattens markets, runs the comparator on the union. Cross-event mode catches "...by May 31" vs "...by Jun 30" patterns that single-event misses. SEMANTIC ANCHOR: cross-event pairs require ≥0.30 Jaccard similarity on question tokens (prevents Powell-Fed-Pause being paired with Powell-DOJ-probe); skipped_low_similarity surfaces the rejected pair count. PARTITION FILTER: drops will-person-X / will-manager-Y / will-someone-else- placeholder slugs; partitions with >20% placeholder fraction return null arb signal. Response: opportunities[] (gap_pp, suggested_trade, reasoning, monotonicity violation context), and in event mode partition_check{sum_yes_prices, gap_from_1, placeholders_filtered, suggested_trade}. FEES: every opportunities[] row and partition_check.arbitrage carry edge_pp_gross (== gap_pp / overround_pp), fees_pp, edge_pp_net, net_positive, plus polymarket_fee_pp, fee_basis and fee_categories[]. BOTH cost components are modeled: Polymarket's own per-category TAKER FEE (fee = shares × rate × p × (1-p), rates crypto 0.07 / sports-economics-culture-weather-other 0.05 / finance-politics-mentions-tech 0.04, geopolitics and world events fee-free; verified against Polymarket's own docs as of 2026-09-13) and Polygon gas (~$0.02/leg). The taker fee dominates: ~$1.75 per 100 shares on a crypto market at 50c versus $0.02 of gas, so rows that looked profitable before fleet #1927 may now show net_positive:false — that is the correction, not a regression. Each leg is priced at ITS OWN market's rate and price (the fee curve peaks at 50c and falls toward both extremes). fee_basis says where the rate came from: 'payload' (read off the market, the normal case), 'category' (mapped from its fee category), 'fee_free', or 'fallback' (rate unknown — charged at the modal 0.05 rather than assumed free, so an unreadable market is never reported as costless). Where fill_check reprices against live depth, this does NOT double-count that spread cost. FILL CHECK: when the partition signal fires, arbitrage.fill_check prices it against live CLOB depth (theoretical_edge_pp_at_book vs realizable_edge_pp at 1000 shares/leg, thin_legs[]) — realizable_edge_pp ≤ 0 means the overround exists only at last-trade, not in the book; do not trade it. For custom sizing use polymarket_fill_risk.ConnectorNo auth
- Requires `checkout:write` or `checkout:link`, or no key: send `meta.ucp-agent.profile` for the same payment link. **Checkout is always human-in-the-loop: it returns a link the buyer opens and confirms — it never charges a card or completes an order on its own.** **Call `set_shipping_address` first unless `fulfillment` is `"external"` (the seller's site collects the address).** Cart total must not exceed the platform cap (`kifly://platform/limits`). **To pre-fill the buyer's email on the payment page, pass `email` — ask the buyer for it in plain language ('what email should the receipt go to?'). Never ask the buyer to paste a token.** Read `payment_rail` on the response BEFORE telling the buyer anything: `'stripe-checkout'` is paid through Kifly, `'directory-handoff'` hands the buyer to the seller's own site to pay, with a tracked link per product and no Kifly payment link, and `'shopify-native'` sends the buyer to the seller's own checkout. **Full response field reference, including every refusal code: read the `kifly://docs/checkout-response` resource.**ConnectorDestructiveNo auth
- List a returning buyer's recent orders and their current fulfillment status — use this in a NEW session to answer 'did my order ship?' / 'where's my package?' when you don't have the original `session_id` from `checkout`. Requires the buyer's `buyer_token` (recover it via `request_buyer_code` + `verify_buyer` if you don't have one). Returns `{ orders, count }`, newest first; each order has `status` (`paid` | `shipped` | `delivered`), `items`, `amount_cents`, `placed_at`, and — once shipped — `tracking_number`, `carrier`, and a public `tracking_url`. **Pass `since` (an ISO-8601 timestamp from a previous check) to get only orders that changed since then** — surface those proactively ('your last order just shipped'). `order_id` identifies the order; `session_id` cross-references `order_status` for a single live checkout.ConnectorNo auth
- List all active sellers on the Kifly network. **Requires a network token (kfn_live_…).** Returns each seller's handle, name, city, region, delivery coverage (`nationwide:true` or a `states` list), delivery fee, and catalog size. `delivery_coverage.cities` may be capped to a handful of entries — compare `cities.length` against `city_count`; if fewer, call `get_seller` for that seller's full city list. Use this to discover which sellers are available and which ship to a buyer's location before calling `get_seller` or `search_products`. **Pagination:** when `kifly:hasMore` is true, pass `kifly:nextCursor` as `cursor` to fetch the next page. Default page size is 20, max 50.ConnectorNo auth
Matching MCP Servers
- FlicenseAqualityDmaintenanceAn MCP server that enables natural language catalog search, cart management, and checkout workflows against the Fake Store API, with strict schemas and session-persistent carts.8-
- AlicenseBqualityBmaintenanceTriggers OLTP order generation, CDC ETL, and fraud evidence pack queries for the Databricks eCommerce analytics lakehouse.9Apache 2.0
Matching MCP Connectors
Traject Data ecommerce MCP — Amazon (Rainforest API) + Walmart (BlueCart API)
Ecommerce store metrics by domain: revenue, ad spend, traffic. Log in to search 600k+ stores.
- Claim a FREE entry pass to an event on the VIA network, directly from discovery. FREE guest-list tiers only (price 0, the kind find_seller / get_seller_products surface at $0). No payment, no wallet, no x402: provide the attendee name and email, and VIA records the place, emails a confirmation, and notifies the organiser. One pass per email / per account. Paid products are NOT claimable here: connect to the seller's per-seller MCP and use buy_product (USDC via x402). Pass the product_id from a find_seller result (mcp_ref.product_id) or get_seller_products.ConnectorNo auth
- Fetch full detail for ONE listing before buying, from anywhere on the network, without leaving this connector. Pass the seller_mcp_url and product_id exactly as they appear in a find_seller / get_seller_products result (mcp_ref.seller_mcp_url and mcp_ref.product_id). Returns the listing with price, stock, and what the purchase requires. This forwards to the owning seller; the same buy loop (get_product -> get_shipping_quote -> buy_product) then settles here.ConnectorNo auth
- Files a concierge switch request with the complete contract data in one call. Intended for autonomous agents that already hold the user's full profile, IBAN and a standing authorization; in a conversation with a person, start-booking opens a form in which the user enters these data. Commerce for Agents stores the request encrypted and an operator submits the contract application to the provider; the user receives a confirmation email at once and the provider's contract documents later. There is no self-service checkout link. Input: the `ref` of the chosen offer plus the contract data. Postal code and city come from the comparison; previousProvider, previousCustomerNumber and meterNumber are printed on the last energy bill. `consent: true` attests that the user explicitly agreed to (1) Commerce for Agents submitting the contract on their behalf, (2) the SEPA direct-debit mandate for the given IBAN and (3) the privacy policy at commerceforagents.com/privacy, either by an explicit yes in the conversation or by a standing authorization given to the agent. The response contains nextSteps for the user.ConnectorDestructiveNo auth
- Use this when the user asks how visible their product results are in Google web Search, and which product pages carry them. Search Console performance for one search appearance, defaulting to MERCHANT_LISTINGS: the appearance inventory of the property, a daily clicks / impressions / CTR / position timeline in date order, and the top pages (product URLs) behind it; appearances and pages are sorted by clicks, highest first, and CTR is a 0-100 percentage. Search Console merchant listings counts enriched product results in web Search only, so it does not reconcile to one figure with Merchant Center free listings. Not for the Shopping tab, Images, Lens, YouTube or Maps: use get_organic_shopping_performance. Always served from the live Search Console API: search appearance is never stored in the GSC Wizard warehouse, and it can be filtered on but never grouped with another dimension. `hasAppearance` is false when the property has no rows for the requested appearance, and `emptyBecause` is set whenever it has no impressions, which is normal for non-ecommerce sites. The window may span at most 16 months (Search Console retention); a longer one is rejected with bad_request. Date range is optional: omit startDate/endDate to analyze the last 28 settled days (data lags ~2-3 days).ConnectorOAuth
- Consulta somente leitura das cotações recentes desta loja, para investigar preço inesperado, serviço ausente ou cotação vazia. Com o supportCode devolvido por get_shipping_rates, mostra aquela cotação; sem ele, lista até 20 cotações dos últimos 30 dias. Cada registro traz serviços e preços devolvidos, serviços excluídos com o motivo e, quando disponível, a memória de cálculo. Não refaz a cotação nem confirma o preço exibido no checkout; ausência de registro não prova que a cotação não ocorreu. source=wix exige vínculo do app configurado pelo operador.ConnectorAPI key
- Prices Kalshi daily high-temperature markets against the NWS forecast for the market's OWN settlement station, and measures whether that forecast actually beats the market. Two modes. LIVE (default): returns the full strike ladder for one city and settlement date with market_prob (mid), forecast_prob, and edge_pp per strike, plus the settlement clause verbatim. BACKTEST (`backtest_days: N`): scores an archived gridded forecast against the market on settled days and returns brier_market vs brier_forecast with a plain-English `verdict`, so the edge is MEASURED rather than asserted. READ THE WARNINGS — they are not boilerplate. (1) These markets DO NOT settle on the NWS. They settle on The Weather Company (weather.com) at a Kalshi station code such as CLINYC, which the response quotes verbatim; so part of every edge_pp is NWS-vs-Weather-Company disagreement about the same day at the same station, which is not mispricing and not tradeable. `settlement_vs_forecast_basis_f` from backtest mode is that part as a number. (2) The station is DERIVED from the settlement clause, never from the city name: Chicago settles at MIDWAY and New York at CENTRAL PARK, so a city-centre forecast would misprice a whole ladder. A station that cannot be resolved yields rows with no forecast and a reason, never a guessed coordinate. (3) forecast_prob assumes a normal distribution around the NWS high whose width is ASSUMED, not fitted (stated in `distribution_assumption`) — run backtest mode to see whether it is calibrated. (4) edge_pp is gross: no Kalshi fees, no bid-ask. MEASURED RESULT, AND IT IS NOT THE FLATTERING ONE: on the first backtest (KXHIGHNY, 13 settled days to 2026-09-11, 58 market observations) the MARKET beat the forecast — Brier 0.1008 for the market against 0.1594 for the archived gridded forecast, lower being better. So on that sample there is NO forecast edge to sell, and a large edge_pp is more likely to be the model disagreeing with a better-informed market than an opportunity. The measured settlement-vs-forecast basis was 1.7F mean absolute over 8 pinnable days, slightly warm-biased, which is a big share of a typical edge_pp on a 2-degree bracket. Re-run backtest_days before believing any edge; if a later sample reverses this, the numbers say so. NWS is US-only, so the ~30 international Kalshi weather series (London, Paris, Tokyo) return market prices with forecast_unavailable rather than a forecast. Precipitation series are listed but not yet priced. Cities: nyc, chicago, los angeles, miami, austin, houston, denver, philadelphia — or pass `series_ticker` for any other (e.g. "KXHIGHTBOS").ConnectorNo auth
- Claygent-style per-row research: answer ONE question about ONE company and return a JSON object matching your output_schema, with every field wrapped in its own evidence — {value, evidence_url, quote, status}. status is NEVER self-reported by the model: "found" means this code independently verified the model's quote is a VERBATIM substring of text actually fetched; "inferred" means a value was given but the quote could not be verified; "not_established" means no source answered the field, and its value is always null — never guessed, never a blended score. Sources: "web" fetches the company's own site (entity.domain required — homepage, /about, /leadership) via fetch_url; "catalog" checks entity_profile (SEC EDGAR; resolved:false for a private company is expected, not a failure); "both" (default) tries both. max_cost (USD, default 0.02, max 0.50) scales how many pages are fetched and refuses up front if it is too small to pay for even one extraction call (floor $0.002) — never silently overspends. A row where every source comes back empty costs nothing: every field is mechanically not_established with NO model call made. For a boolean/derived field (e.g. "does this company sell to healthcare"), the quote only has to SUPPORT the value — a descriptive sentence about customers/products counts, the source need not state the answer verbatim. leadership_page_status ("fetched"|"not_found"|"not_attempted", plus leadership_note) says plainly whether a leadership/team page was actually read, so a named-person field (head_of_sales) coming back not_established is distinguishable from "this company just doesn't publish one" vs. "we never checked". model_output_empty:true means the model returned nothing usable (a transport/budget problem) — every field is not_established for THAT reason, never read as 20 individual "no" judgments. Use with a fixed question + schema across many rows for "Claygent over N companies with a hard cost cap" (composes with batch callers). For picking from a fixed label list instead of extracting open fields, use classify_row (cheaper, one model call).ConnectorNo auth
- Tell the Pipeworx team something is broken, missing, or needs to exist. Use when a tool returns wrong/stale data (bug), when a tool you wish existed isn't in the catalog (feature/data_gap), or when something worked surprisingly well (praise). ONLY for tools served by this Pipeworx connection — if the tool came from a different MCP server in your client (another vendor's Gmail, Splunk, Slack, etc. connector), we cannot fix it and reporting it here only delays you; file it with that server instead. Not sure? Pipeworx tool names are the ones this connection lists. Describe the issue in terms of Pipeworx tools/packs — don't paste the end-user's prompt. Filing without an account returns a `claim_token`; pass it back later as pipeworx_feedback({claim_token:"pwfb_…"}) to read whether it was fixed and what changed. The team reads digests daily and signal directly affects roadmap. Rate-limited to 5 per identifier per day. Free; doesn't count against your tool-call quota.ConnectorNo auth
- Reveal data for stores. THIS SPENDS CREDITS. Before you call it, call getRevealCost for the same selection and tell the user the cost, or state the cost of 1 credit per store, then ask the user to confirm. Never call it without the confirmation. details unlocks the profile links, buying signals and phone. ceo, marketing and ecommerce start a decision-maker contact search (1 credit per store, +1 for a store whose details are not revealed yet). A store you already revealed costs 0. If you have too few credits, the result shows the cost and your balance, and nothing is charged. Use getRevealStatus to follow a contact search.ConnectorDestructiveNo auth
- Create a signal set, or replace the criteria of an existing one. Without setId it creates a new set (the plan limit applies). With setId it updates that set and replaces all its signals, legacy categories and ICP filters with the new criteria. Conditions that you did not set (saved custom SQL conditions) stay on the set, joined with AND. Then the reply has preservedConditions, the number of these conditions. Use previewSignalSet first to check that the criteria match enough stores. Paid plans only.ConnectorDestructiveNo auth
- Delete an item (a Bundles offer, a popup campaign, a bar). The delete is saved as a draft with a preview card and happens when it is published (the merchant's Publish click, or publish_draft where AI publishing is allowed); until then the item stays live and the draft can be discarded. A published delete can be undone (undo_publish restores the item). Call this only when the merchant asked for it in this conversation and pass their words in `user_request`.ConnectorDestructiveNo auth
- Search the Vivid Ads catalogue by product name, category, or intended use (e.g. 'corflute', 'pull up banner', 'expo', 'shopfront'). Returns matching products grounded in Vivid's own Shopify collections, so it also surfaces same-range, same-purpose alternatives — products flagged `sameRange:true` come from the top match's curated collection (returned as `collection`). ALWAYS mention these to the customer (e.g. 'we have two Pull Up Banner options, and Fabric Banner Stands do the same job'). Treat a from-price as INDICATIVE only — use vivid_product for options then vivid_price for the exact configuration. Paginated: returns `total`, `has_more` and `next_offset`; pass `offset` to get the next page.ConnectorNo auth
- Return the secure payment link for a formal quote Vivid already emailed (e.g. #D786069) so the customer can complete the order without leaving the conversation. Requires the quote number AND the email it was sent to (identity). Read-only — nothing is charged; it returns the customer's existing Shopify checkout link. If the quote has already become an order, it says so instead of issuing another link. CODE REQUIRED: needs the customer's email AND a verified identity token. Without a token this tool emails the customer a 6-digit code and returns status need_verification with a verificationId — ask the customer for the code, call vivid_identity_verify, then call this tool again with the token. It shows nothing before that.ConnectorNo auth
- Check a customer's DIGITAL PROOF status: has the proof been emailed, is it awaiting their approval, being revised after rejection, or already approved (production underway). Use for 'where's my proof', 'did you send my proof', 'when do I approve'. Requires the order number AND the email on the order (identity — details only return when they match). Relay the returned agent_hint concisely; production starts only after the customer approves the emailed proof. CODE REQUIRED: needs the customer's email AND a verified identity token. Without a token this tool emails the customer a 6-digit code and returns status need_verification with a verificationId — ask the customer for the code, call vivid_identity_verify, then call this tool again with the token. It shows nothing before that.ConnectorNo auth
- Reorder a customer's previous signage job — fast. Requires identity verification (emailed one-time code), not just an order number. action:'list' shows their past orders; action:'reorder' repeats one. ARTWORK: it reuses only the customer's previously APPROVED artwork (the print file), never a pre-approval upload; if it can't be confirmed automatically the team confirms it. A fresh proof is ALWAYS re-issued to confirm the artwork before printing. The customer may also supply new artwork or change the quantity. Re-prices with CURRENT pricing (never the old price). Creates a proof-gated draft order; never charges a card. CODE REQUIRED: needs the customer's email AND a verified identity token. Without a token this tool emails the customer a 6-digit code and returns status need_verification with a verificationId — ask the customer for the code, call vivid_identity_verify, then call this tool again with the token. It shows nothing before that.ConnectorNo auth