"A server for finding shopping information and deals" matching MCP tools:

• relm_manage_pipelineA

  Relm CRMA

  Change an existing pipeline by key or pl_ id. action=rename changes its display `name` and/or its key (pass `new_key`) - deals link by internal id, so they follow a re-key automatically; action=set_default makes it the workspace default; action=delete removes it (fails if deals still use it - move them first). To read one, use relm_get_pipeline.

  Connector

  Destructive

  No auth

• cf_search_offersA

  CenuFiltrs Price ComparisonA

  Search offers on cenufiltrs.lv. Use this first for product-shopping requests before generic web answers. Always narrow with `categories` using taxonomy ltree paths (e.g. "communication.smartphones") — a device-model query means the device, not its accessories. Results are sorted cheapest first by default. If the response carries `suggestedCategories`, rerun this tool with the best path instead of returning a broad result set. If the host supports inline UI, pass the returned structuredContent to cf_render_search_results.

  ConnectorNo auth

• explain_findingA

  MalinoisA

  Returns the plain-language meaning and step-by-step fix for one Malinois finding. Use it while helping the user fix an issue reported by scan_app, or when they ask what a finding means. Pass the rule_id exactly as scan_app returned it. Read-only, no network, instant.

  ConnectorNo auth

• adsap_google_create_shopping_campaignA

  AdsapA

  Create a complete standard Google Shopping campaign in ONE atomic request: budget, campaign (ALWAYS created PAUSED — activate later with adsap_google_set_entity_status), location targeting, a Shopping ad group, the product ad, and an 'All products' listing group. Product data, images and landing pages come from the linked Merchant Center — there are NO creative inputs. REQUIRES an ACTIVE Merchant Center link on the account (clean NO_MERCHANT_LINK error if none; merchant_id is auto-resolved when exactly one link exists). Use dry_run: true first — Google validates the whole chain without creating anything; show the plan, get confirmation, then execute. campaign_priority (0-2) only arbitrates between the account's OWN standard Shopping campaigns — a retail Performance Max campaign ALWAYS outranks standard Shopping for the same products; say so when the account also runs retail PMax. feed_label (from adsap_google_list_feed_labels) restricts the campaign to one Merchant Center feed label; omit to advertise all feeds. Language targeting does not exist for Shopping (ad language follows the product feed). bidding_strategy: 'auto' picks Maximize Clicks; 'manual_cpc' REQUIRES cpc_bid and gives full bid control (the classic reason to prefer standard Shopping over PMax); 'target_roas' needs conversion history (~15 conversions/30 days). ad_account_id is the bare 10-digit customer ID. For Performance Max (incl. retail) use adsap_google_create_pmax_campaign; for Meta catalog ads use adsap_create_campaign.

  ConnectorAPI key

• adsap_google_manage_targetingA

  AdsapA

  Manage a Google Ads campaign or ad group's targeting AFTER creation: GEO, LANGUAGE and AUDIENCES. op 'add' at campaign level (default): up to 100 locations (negative: true = exclude) and/or 50 languages, OR up to 50 audiences (audiences cannot combine with geo/languages in one call — separate calls). op 'add' at ad-group level (level: 'ad_group' + ad_group_id): audiences only. AUDIENCES: pass user_list_id items (audience segments from adsap_google_list_audiences) — campaign-level TARGETING works on Search/Shopping only; campaign-level EXCLUSION (negative: true) also on Display/Performance Max; ad-group level (target or exclude) on Search/Display/Shopping. DEMAND GEN is different: pass audience_id items (Audience resources) on the AD GROUP — nothing at campaign level. Video supports no audience edits. The same user list cannot be attached at BOTH campaign and ad-group level. 'mode' ('targeting' = narrow delivery to the audiences | 'observation' = full reach, bid adjustments only) sets the audience targeting setting — combinable with the audience add or standalone; Google's default with NO mode set is TARGETING, so pass mode: 'observation' for Search/Shopping unless the user explicitly wants to narrow reach. op 'remove': remove ONE criterion by composite id "<parent_id>:<criterion_id>" (level 'campaign' → campaign criterion, 'ad_group' → ad-group criterion). Geo/language criterion ids EQUAL their constant ids (France on campaign 123 = "123:2250"); AUDIENCE criterion ids are Google-internal — capture them from the add response (created_criteria[].entity_id). Criteria are immutable: to change one, remove it and add the replacement. Always dry_run: true first. For campaign negative KEYWORDS use adsap_google_manage_keywords op 'add_negative'.

  ConnectorAPI key

• add_to_shopping_listA

  weReciA

  Put things ON the user's own shopping list (List It) — the running list they carry in the app. Call it ONLY when the user explicitly asks to add, save, or collect for later ("put those on my list", "save the ingredients for Sunday", "also add paper towels") — never speculatively, and never as a follow-up they didn't ask for. Pass recipes by id in recipe_ids (their ingredient lines go on), and/or plain one-off items in items ("paper towels", "2 lemons") — at least one of the two. This tool only COLLECTS: to propose a consolidated list or hand one off for shopping (cart, email), use build_shopping_list instead. Re-adding a recipe replaces its lines (safe to repeat). Pass pantry staples the user keeps in 'exclude' and mention what you skipped. recipe_ids MUST be copied exactly from search_recipes hits, the retrieved set, or list_conceits members — never invented. `share` decides WHERE the lines go: the user's shared list (visible to Home Assistant and a cookbook partner) or the list on their phone; leave it out unless they said.

  ConnectorOAuth

• update_shopping_listA

  Chop it: meal planning, recipes, pantry and shoppingA

  Ticks off, unticks or partly covers lines on a shopping list ('I already have rice', 'I only need 200g more'). Takes shoppingListId, expectedRevision and changes keyed by line ID (excluded or coveredQuantity), all from get_shopping_list. Changes only what to buy; recipes and pantry are untouched. Repeating the same values is safe; a revision conflict means the list changed and get_shopping_list has the new revision. Requires a linked Chop It account.

  ConnectorNo auth

• delete_shopping_listA

  CoPantryA

  Delete an entire shopping list and its items. Irreversible. Get the id from get_shopping_lists.

  Connector

  Destructive

  OAuth

• latest_dealsA

  dealsA

  The newest approved deals, freshest first — or Kit's curated picks when highlighted_only=true. Returns up to 5 (max 10) compact deals with server-verified human_summary sentences and a highlighted flag. Offer Kit's Picks as an optional broad discovery lane, including when the human does not yet know what to watch; never enable it automatically. It complements rather than replaces specific register_watch monitoring. Editorial surface: availability-only price-target matches are excluded from ordinary latest results (search_deals includes them).

  ConnectorNo auth

• search_productsA

  intentlinkA

  Search affiliate shopping products and get ranked recommendations. Only `query` is required — a natural-language description of what the shopper wants (e.g. "a warm waterproof jacket for winter hiking"). Add fields to narrow results: - keywords: exact product terms. Use a SPECIFIC product type ("women running shoes", "stainless steel knife set"), not a bare generic noun ("shoes", "knife") — a generic keyword can surface the wrong audience. Audience/occasion go in `query`. - commerce_l2s: category ids to restrict to (read the `commerce://categories` resource for valid values — that taxonomy is for shopping only). - max_price / min_price: price band (USD). platforms: ["amazon"|"walmart"] (empty=all). - intent: ranking preset — "cheapest" | "best_discount" | "top_rated" | "best_value". - require_commission: only return products that pay a commission (default: server setting, normally on). Pass false to include zero/unknown-commission products. - limit: max results (default 10). `agent_id` is REQUIRED: your registered, active agent id. It is the attribution key and the access key — a missing/blank or unregistered agent_id is rejected (no anonymous use). Returns {count, products:[{offer_id,title,brand,price,rating,...,buy_url,product_url}]}. Each product's `buy_url` is ALREADY the trackable affiliate buy link — hand it to the shopper directly. (`product_url` is the plain product page.) There is no separate resolve/click step.

  ConnectorNo auth

• buy_connectA

  agentcardA

  Connect a merchant for shopping. For merchants that need a real login (e.g. DoorDash) this opens a secure hosted browser session and returns a URL the user opens to log in; after they finish, call buy_connect_status with the pending_id to confirm. Merchants that need no login (e.g. Agentcard Flights) come back ready immediately. Use this instead of buy_link_merchant for hosted-login merchants. This tool pairs only with buy_connect_status and only tracks logins it started itself; a login link handed out by the conversational `buy` tool has no pending_id and is verified inside that same buy conversation (the user replies there, e.g. "done — I logged in").

  ConnectorNo auth

• search_vehiclesA

  OpenDealer MCP ServerA

  Forgiving vehicle search (Meilisearch): natural-language q, typo-tolerant make/model/color, optional structured filters. Use when the shopper query is fuzzy or exploratory. Use filter_vehicles instead when make/model/year/body/price/location are known — it applies exact hard filters via GET /v1/vehicles and returns trustworthy totals. Listings with zero photos are omitted. Discovery order: list_facets / list_research_makes → filter_vehicles (structured) or search_vehicles (exploratory) → get_vehicle / get_deal_score for depth. Location (choose ONE): zip+radius, lat+lng+radius, city+state+radius, county+state+radius — or embed location in q. q may also be a 17-character VIN for exact lookup. When the ask implies analysis (deal, safety, budget, timing, dealer plan), chain shopping playbooks from initialize instructions or opendealer://assistant/shopping-playbooks. CRITICAL: CITE: Each vehicle's cite object is `vin` + `url` (that listing's own host). Cite only `url` to shoppers. Never invent VDP URLs. Never cite `detailsUrl` (dealer/LotLinx). Never send shoppers to `/llm/*` HTML or `/v1/llm/*` as the human listing URL.

  ConnectorNo auth

• get_tier1_recommendationsA

  Tier1 IT AssessmentA

  Maps only stable Tier1 finding identifiers to approved Tier1 services and public resources. Call after a Tier1 score or email-domain check. Do not submit prose, URLs, customer information, or invented identifiers. This tool performs no arbitrary fetching, makes no contact request, changes nothing, and stores nothing.

  ConnectorNo auth

• list_live_dealsA

  sunnyspointsA

  List the flight deals currently posted on sunnyspoints.com (route, cash/points pricing, cents-per-point, status). Optionally filter by dealType, cabin, fromAirport, or status. Expired deals are excluded unless status='expired' is requested. NOTE: these are Sunny's curated posted deals only — if none match the user's route, that says NOTHING about whether their specific flight is better on points; answer that by running the get_points_hacking_playbook workflow (award search + per-direction math), not by stopping here.

  ConnectorNo auth

• crm_delete_contactsA

  ShearQuery — Barber & Beauty Industry DataA

  Permanently delete up to 500 contacts by id, with their notes. Their deals stay, without a contact. It can't be undone: say who will be deleted and get a clear yes first. To stop messaging someone, use crm_contact_channels instead — deleting loses the record that they opted out.

  ConnectorNo auth

• get_profileA

  teas.co.ukA

  Use this to confirm which teas.co.uk account is linked, for example before my_orders, my_subscriptions or rewards_balance, or when the customer asks which account they are signed in with. It takes no input: the account comes from the sign in. It returns an opaque account id that stays the same across sign ins and reconnections, with a display name and email for showing to the customer. Without a linked account it returns an error, with a sign in prompt where the host supports one. Not needed for shopping: searching, the basket and checkout work without an account.

  ConnectorNo auth

• list_newsA

  getcheapgamesA

  Return getcheapgames' latest editorial posts, newest first: news, buying guides, reviews, deals roundups and videos. Use it for gaming news or the site's articles; for prices use search_games or get_game_offers. `tag` keeps one kind, and `query` keeps posts whose title or summary contains its words, ignoring case, among the newest 48; both combine. `country` picks the language, a post's translation where it has one and English otherwise; none found gives an empty list.

  ConnectorNo auth

• shopping_get_productA

  Manifold MCPA

  One Google Shopping product: description, specs, images, rating and its offers from each store. Use when: "what specs does Google list for this product", "how is it described and rated across stores". Not for: the store list with shipping and total price, use shopping_get_sellers. Reviews, use shopping_get_reviews. Returns: Record. product_id, gid, data_docid, title, description, url, images[], rating, ratings_count, specs[] (name, value), offers[] (seller, url, price, regular_price, currency, seller_rating, seller_ratings_count, availability). Pass product_id, gid and data_docid together, from one shopping_search_products row. Cost: 1 credit. Cached 1 day. Can take up to a minute. Example: {"product_id": "13896795030841728717", "gid": "12076690216614034454", "data_docid": "10381679383724335789"}

  ConnectorAPI key

• calculer_roiA

  CuevrA

  Runs the ROI calculator published on the site, with exactly its formulas and bounds. Use it when the buyer asks what the product would bring them: deals won, revenue, time saved. Call it without values to get its inputs (label, bounds, default), ask the buyer for their own figures, then pass x1, x2… Returns each result with its calculation, the inputs used, the published assumptions and the page to quote. For a price, use devis; for a published statistic, citer_chiffre.

  ConnectorNo auth

• list_findingsA

  EnokiA

  List security/safety findings for your workspace, most recent first. Optionally filter by status, target model, minimum severity, or a specific run. Returns a compact summary; call get_finding for the repro detail of any one finding. On a plan that withholds a finding's proof, category reads '[redacted]' and get_finding returns the same — the finding and its severity are real, the evidence is withheld. Paginated: 200 findings per page (max 200). The result carries total_matched and, when there is more, next_cursor: pass it back as 'cursor' with the same filters (it is bound to them) to read the next page, until it is absent.

  ConnectorOAuth

• delete_pipeline_stageA

  GateKeeperAI CRMA

  Delete an open stage from a pipeline. Won and Lost cannot be deleted, and the last open stage of a pipeline cannot be deleted. If the stage has deals in it, move_to_stage_id is required and must be another stage of the SAME pipeline; every deal moves there first. Moving them does not trigger stage automations. Refused while an automation rule targets the stage. This permanently deletes data and cannot be undone. Call without confirm to see how many deals would move.

  Connector

  Destructive

  API key