Plugin tracker

Tools

Explore what tracked Claude Connectors and ChatGPT Plugins can actually do. Search by tool, Plugin, Brand, category, verb, or access requirement.

Latest snapshot2026-09-13USmethodology registry-public-v1

Searchable tools

119,491

Authless tools

7,773

Auth required

107,252

Described tools

64,388

119,491 tools

Get Transactionsget · Fetch the full transaction (modification) history for an award. Every modification, option exercise, and de-obligation is a transaction. Modification number '0' is the original base award. Use to understand the full lifecycle of a contract including its descriptive text at each point in time. Returns per transaction: id, type, action_date, action_type, modification_number, description, federal_action_obligation.USAspending MCP1102toolsPluginnoneOperations
List Federal Accountslist · List Treasury federal accounts (TAS) with budgetary resources. keyword filters by account name or AID. fiscal_year defaults to current FY. sort is a dict like {'field':'budgetary_resources','direction':'desc'}.USAspending MCP1102toolsPluginnoneOperations
List Stateslist · List all states with their FIPS codes and award totals. Returns the full list of US states/territories with FIPS codes you can pass to get_state_profile(). The /recipient/state/ endpoint returns a JSON array (not an object). We wrap it in {"results": [...]} to keep the tool return type consistent with every other endpoint in this MCP.USAspending MCP1102toolsPluginnoneOperations
List Toptier Agencieslist · List all top-tier federal agencies tracked by USASpending. Returns agency codes, names, abbreviations, and current-year budgetary resources. Use the returned 'toptier_code' values with get_agency_overview().USAspending MCP1102toolsPluginnoneOperations
Lookup PIIDlookup · Look up awards by PIID or PIID prefix with automatic award-type detection. Convenience tool: tries contracts first, then IDVs if no match. Uses keyword search under the hood, which behaves as a substring match on the PIID field, so you can pass a full PIID or a contracting-office prefix (e.g. 'N00024' for NAVSEA, 'W91CRB' for Army Contracting Command, 'FA8650' for AFRL). Returns the matching awards with basic fields. Use get_award_detail() with the returned generated_internal_id for the full record. Handy for enriching PRISM, Contract Court, or FPDS exports where you have a PIID but don't know whether it's a contract or IDV.USAspending MCP1102toolsPluginnoneOperations
New Awards Over Timenew · Pipeline trend of new awards to a recipient over time. REQUIRES recipient_id (the recipient hash with -P suffix for parent-level rollup, or -R for a single recipient). Returns counts of new awards grouped by month, quarter, or fiscal year. The endpoint rejects calls without recipient_id with HTTP 422, and it also requires a time_period. When you omit the dates, a default range covering all searchable data (2007-10-01 through 2099-09-30) is sent automatically.USAspending MCP1102toolsPluginnoneOperations
Search Awardssearch · Search federal awards (contracts, IDVs, grants, loans, etc.) on USASpending.gov. This is the primary workhorse for finding awards. Returns matching awards with standard fields (Award ID, Recipient, Description, Amount, Agencies, NAICS, PSC, dates). Use get_award_detail() with the generated_internal_id from results to get full award details. Important rules: - award_type groups cannot be mixed; pick one category per call - time_period_start/end use YYYY-MM-DD format - award_amount_min/max are in USD - place_of_performance_state is a 2-letter USPS code (e.g. 'MD', 'VA') - For loans, use award_type='loans' and sort='Loan Value' - def_codes filters to Disaster Emergency Fund codes (COVID-19, IIJA, IRA supplementals); see get_def_codes_reference() for the list Filtering to specific contracting commands (NAVSEA, AFRL, etc.): USASpending's subtier level is at the service branch (Department of the Navy, Army, Air Force), not the contracting command. To filter to a specific command, use keywords with the PIID office prefix instead: - NAVSEA contracts: keywords=['N00024'] - Army Contracting: keywords=['W91CRB'] - AFRL: keywords=['FA8650'] - NAVAIR: keywords=['N00019'] This performs a substring match on the PIID field and is more reliable than the award_ids filter for partial matches. Common filter value references: - set_aside_type_codes: SBA, SBP, 8A, 8AN, HZC, HZS, SDVOSBS, SDVOSBC, WOSB, WOSBSS, EDWOSB, EDWOSBSS, VSA - extent_competed_type_codes: A (Full & Open), B, C, D, E, F, G, CDO, NDO - contract_pricing_type_codes: J (FFP), Y (T&M), Z (LH), U (CPFF), V (CPIF), R (CPAF), L (FP Incentive), M (FP Award Fee) IMPORTANT: awarding_agency/funding_agency must be the FULL TOPTIER NAME, not a slug. Use 'Department of Defense', NOT 'department-of-defense'. Slugs silently return zero results, and so does any name that is not a toptier agency: the military departments are SUBTIERS, so pass awarding_agency='Department of Defense' with awarding_subagency='Department of the Navy' (never 'Department of the Navy' as awarding_agency). A mismatched pair (a subagency that does not belong to the given toptier) also silently returns zero results. Use list_toptier_agencies() and get_agency_sub_agencies() for exact names. Result caveats: recipient_name matches corporate affiliations, so a parent-company search can return joint ventures whose display names share no text with the query (a Hanford JV surfaces under 'Leidos'); verify names before presenting a definitive list. Large pulls can exceed MCP client payload budgets (limit=100 has measured ~90K characters); page in batches of 25-30 for big result sets.USAspending MCP1102toolsPluginnoneOperations
Search Recipientssearch · Search USASpending recipients (vendors and grantees) by keyword. Returns paginated recipients with their UEI, DUNS, name, and a recipient 'id' that downstream tools use as the hash for get_recipient_profile and get_recipient_children. keyword can match recipient name, UEI, or DUNS. If omitted, returns the top recipients ranked by `sort`.USAspending MCP1102toolsPluginnoneOperations
Search Subawardssearch · Search FFATA subaward reports on USASpending. Returns the FFATA subaward records (subcontracts under prime contracts and subawards under prime grants). Complementary to the SAM.gov FFATA endpoints but expressed at the USASpending data model. award_id: optional generated_internal_id (CONT_AWD_..., ASST_NON_..., etc.) to scope subawards to a single prime award. If omitted, returns subawards across all primes for the page. Pagination uses page (1-indexed) and limit (1-100).USAspending MCP1102toolsPluginnoneOperations
Spending Over Timespending · Aggregate spending amounts over time, grouped by fiscal year, quarter, or month. Use this to visualize spending trends, identify fiscal-year-end spikes, or compare spending patterns across years. Note: The API returns fiscal_year as a STRING. Cast to int for numeric comparisons. awarding_agency must be a TOPTIER agency name ('Department of Defense'). Military departments are subtiers: pass awarding_subagency='Department of the Navy'. A non-toptier name in awarding_agency (or a subagency that does not belong to the given toptier) silently returns all-zero aggregates. At least one filter is required (the API rejects empty filter sets with HTTP 400). Typical usage: pass time_period_start + time_period_end.USAspending MCP1102toolsPluginnoneOperations
Spending by Categoryspending · Aggregate spending by a dimension (top vendors, top agencies, top NAICS, etc.). The 'category' parameter controls the grouping dimension. Common uses: - category='recipient': top vendors for a filter set (vendor landscape analysis) - category='awarding_subagency': which contracting offices within an agency - category='naics': which work categories got the most spending - category='psc': which product/service codes got the most spending - category='state_territory': geographic distribution - category='cfda': grant assistance listings Note: recipient category returns vendor names in ALL CAPS and may contain duplicates (subsidiaries, rebrands, re-registrations). For precise market share, apply name normalization to the returned 'name' field. At least one filter is required. An unfiltered call would silently aggregate the entire USASpending database (all years, all agencies), which is never what a caller wants.USAspending MCP1102toolsPluginnoneOperations
Spending by Geographyspending · Geographic breakdown of spending. scope: 'recipient_location' (where the recipient is) or 'place_of_performance' (where the work happens). geo_layer: 'state', 'county', or 'district'. At least one filter is required. The API returns HTTP 500 on an empty filter set, so the requirement is enforced here with a clear error.USAspending MCP1102toolsPluginnoneOperations
Spending by Subaward Groupedspending · Search subawards using the standard filters object (grouped result set). Unlike search_subawards which is scoped to a single prime, this returns subawards grouped under their primes given a filter set similar to search_awards. Useful for FFATA-wide analysis ("show me all DoD subcontracts on cyber awards in FY2026"). sort accepts: award_id, subaward_count, award_generated_internal_id, subaward_obligation. (These differ from search_subawards, which sorts by amount/action_date/etc.) Anything else returns HTTP 400 from the API.USAspending MCP1102toolsPluginnoneOperations
Spending by Transactionspending · Search at the transaction (modification) level. Unlike search_awards which returns one row per award, this returns one row per transaction (initial action plus every modification). Useful for tracking obligation events over time, ceiling adjustments, deobligations, and admin mods. recipient_uei is matched through the API's recipient text search (which covers name, UEI, and DUNS), so pass the plain 12-character UEI. Returns standard transaction fields: Action Date, Mod, Award ID, Action Type, Awarding Agency, Recipient Name.USAspending MCP1102toolsPluginnoneOperations
Coming soon (on-sale radar)scenef · Films whose first SF screening is more than 48 hours out, sorted by first night — the on-sale radar for runs worth booking early. Configurable horizon. In "detailed" mode every showtime also carries its confidence level, source tier, reporting sources, and verified_at timestamp.SceneF — SF ShowtimesSceneFPluginnoneConsumer & Lifestyle
Discount gridscenef · Every structured discount across all SF theaters — venue, label, detail, and day-bound days — with the ones that apply today flagged.SceneF — SF ShowtimesSceneFPluginnoneConsumer & Lifestyle
Film detailsscenef · The full card for one film: title, year, runtime, genres, directors, cast, overview, rating, trailer and poster urls when present, every upcoming showtime with venue/time/ticket link, and a last-night flag when the run is ending. In "detailed" mode every showtime also carries its confidence level, source tier, reporting sources, and verified_at timestamp.SceneF — SF ShowtimesSceneFPluginnoneConsumer & Lifestyle
Plan a movie nightscenef · The concierge: give it a window and a taste profile and it returns 2-4 complete plans — film + specific showtime + theater + why it fits — each with ticket and calendar links, plus one wildcard pick outside the stated genres. Rankings are pure preference-fit; never pay-ranked. In "detailed" mode every showtime also carries its confidence level, source tier, reporting sources, and verified_at timestamp.SceneF — SF ShowtimesSceneFPluginnoneConsumer & Lifestyle
Right nowscenef · The cheap is-anything-on call: how many screenings tonight, the next 5 curtains city-wide with venue/time/film, and dataset freshness per source. In "detailed" mode every showtime also carries its confidence level, source tier, reporting sources, and verified_at timestamp.SceneF — SF ShowtimesSceneFPluginnoneConsumer & Lifestyle
Search showtimes for a filmscenef · Upcoming showtimes for one film (title or slug; fuzzy-matched — ambiguous queries return candidates), grouped by theater with local times, tags (35mm/qa/sold-out), the night each show belongs to, and a ticket link per showtime. Optional date, time window, and venue filters. In "detailed" mode every showtime also carries its confidence level, source tier, reporting sources, and verified_at timestamp.SceneF — SF ShowtimesSceneFPluginnoneConsumer & Lifestyle
The accuracy recordscenef · Accuracy is computed, not claimed: every showtime carries a confidence level, a source tier, and a last-verified time, and the running record of our own verification checks — failures included — is public at https://scenef.com/api/accuracy. This tool returns that record: the site-wide confidence mix, the counts of verification checks confirmed / missing / unreachable over the record's window (window_days in the payload — 30 days at present) with the pass rate and the exact denominator it was computed from, the same per venue with source tier and last-verified time, and the definitions of every level. Checks that could not run — a bot wall, a client-rendered page — are graded unreachable and excluded from the pass rate rather than counted as passes. Quote these numbers directly; they are recomputed on every call.SceneF — SF ShowtimesSceneFPluginnoneConsumer & Lifestyle
Theater infoscenef · One SF theater's card: address, neighborhood, website, ticketing note, structured discounts (label/detail/day), amenities, its next 5 showtimes with ticket links, and its calendar feed url. In "detailed" mode every showtime also carries its confidence level, source tier, reporting sources, and verified_at timestamp.SceneF — SF ShowtimesSceneFPluginnoneConsumer & Lifestyle
What's playing in SFscenef · Ranked list of films playing San Francisco theaters in a given window (tonight, tomorrow, the weekend, or a date), with optional genre and format filters. When the window covers tonight, opens with Notable tonight — scarcity facts with evidence (measured seat counts, final nights, lone prints, posted discounts, live elements); lead with those when asked what to see. Each entry carries year, runtime, genres, a one-line hook, venue count, the next showtime, and the film's SceneF url. In "detailed" mode every showtime also carries its confidence level, source tier, reporting sources, and verified_at timestamp.SceneF — SF ShowtimesSceneFPluginnoneConsumer & Lifestyle
Get Progressget · Hours logged vs. material-participation goal per property (STR 100h, LTR 750h by default), year-to-date, with on-pace status (percent of goal vs. percent of the year elapsed).HourProofHourProofPluginrequiredOperations
List Activitieslist · List the user's logged activities, newest first. Filterable by date range, property, category. (searches the most recent 2000 entries)HourProofHourProofPluginrequiredOperations
List Bookingslist · Guest bookings recorded in the user's HourProof account (guest name, check-in/check-out dates), sourced from the user's connected iCal feeds (Airbnb/VRBO/Hospitable).HourProofHourProofPluginrequiredOperations
List Propertieslist · List the user's rental properties (id, name, type STR/LTR, goal hours). Call before logging to a property.HourProofHourProofPluginrequiredOperations
Log Activitylog · Log a material-participation activity (time spent on a rental property) to the user's HourProof account.HourProofHourProofPluginrequiredOperations
Refresh Progressrefresh · Refresh the progress card data (called by the card UI, not the model).HourProofHourProofPluginrequiredOperations
Create a Promptercreate · Use this when the user wants to save a prompt, script, or teleprompter text to their SuperPrompter account. Omit folder_id unless requested.SuperPrompterNömadPluginrequiredContent & Design
Create a Prompter foldercreate · Use this when the user explicitly asks to create a one-level folder for their Prompters. Repeated calls with the same name reuse it.SuperPrompterNömadPluginrequiredContent & Design
List Prompter folderslist · Use this when the user wants to see their folders or when a named folder must be resolved before creating or moving a Prompter.SuperPrompterNömadPluginrequiredContent & Design
List Prompterslist · Use this when the user wants to find or browse Prompters in their SuperPrompter account, optionally by folder, favorite state, or text.SuperPrompterNömadPluginrequiredContent & Design
Open a Prompterget · Use this when the user wants to read one Prompter or before updating it so the latest body and updated_at value are known.SuperPrompterNömadPluginrequiredContent & Design
Update a Prompterupdate · Use this when the user explicitly wants to change an existing Prompter's title, body, language, folder, or favorite state. Call get_script first and pass its updated_at value.SuperPrompterNömadPluginrequiredContent & Design
analyzeLabelanalyzelabel · Evaluate a product label the user PASTED AS TEXT in this conversation, using the real BioStacks scoring engine: per-ingredient dose vs clinical range, form quality, upper-limit breaches, synergies/conflicts, and an estimated overall score. Use whenever the user pastes an ingredient list or Supplement Facts text for a product that isn't in our catalog (searchProducts came back empty). Transcribe the label rows EXACTLY as pasted — same numbers, same units; put standardizations or branded forms (e.g. 'KSM-66', '24% saponins') in notes. NEVER call this from memory of a label from an earlier turn or from training data — if the label text isn't visible in the conversation, ask the user to paste it again instead.BioStacksBioStacksPluginnoneHealth & Wellness
analyzeStackanalyzestack · Analyze a list of supplement products as a stack: aggregated nutrient totals (with RDA percentages), upper-limit / interaction / harmful-ingredient warnings, beneficial synergies, optimization tips, and an overall safety score. Use when the user lists multiple products together (e.g. 'I take X, Y, and Z — anything wrong?'). Accepts up to 10 product ids.BioStacksBioStacksPluginnoneHealth & Wellness
getIngredientgetingredient · Get clinical data for a nutrient or ingredient: RDA, upper limit, therapeutic dose range, evidence level, related health areas, and which forms to avoid. Use for any question about a single ingredient (e.g. 'how much vitamin D should I take', 'best form of magnesium', 'is biotin good for hair').BioStacksBioStacksPluginnoneHealth & Wellness
getProductgetproduct · Get the full clinical profile for one product by id or slug: quality score, ingredient-by-ingredient dose quality, bioavailability form notes, synergies, conflicts, flagged excipients, per-SKU third-party certifications, and the brand's testing practices. Use whenever the user asks about a specific named product, wants a score explained, asks whether a product/brand is lab tested or certified, or wants to compare products (call this multiple times in parallel for a comparison). Also resolves the user's own saved smart-scan products by id — these return isCustom: true and have no public product page, so never link to one. ALWAYS call this tool (never answer from prior searchProducts results in text) whenever the user selects, taps, or names a specific product, or gives a product id/slug — its score-card widget is the answer.BioStacksBioStacksPluginnoneHealth & Wellness
searchProductssearchproducts · Search supplements by health goal (dimension), nutrient ids, product/brand name, and optional price ceiling. Filters combine — pass `{ dimension: 'general_health', query: 'men' }` to rank men's multis, or `{ dimension: 'sleep', query: 'powder' }` for sleep powders. Returns up to 20 products ranked by clinical efficacy (quality score for general queries, dimension score when a dimension is specified, with a specialist boost when nutrients are specified — so a dedicated vitamin D supplement outranks a multivitamin that happens to include vitamin D). When quoting a product's score to the user, always use qualityScore (the number on the user's product card), never dimensionScore. Provide at least one filter: query, dimension, or nutrientIds. ALWAYS call this for ANY question about a specific supplement, product, brand, or a 'best X for Y' request — including when the user pastes a product link or names one product. Do not answer supplement-product questions from your own knowledge; BioStacks has dose- and form-level scoring your training lacks.BioStacksBioStacksPluginnoneHealth & Wellness
Check order statusget · Check progress of an order THIS conversation placed, using the orderId you were given when it was placed. ALSO SEND orderTrackingToken if the placement returned one. Keep it for the rest of the conversation: without it this lookup stops working if the connection is re-established, and with it the order stays checkable. Tell the customer the customerStatus — it is written to be said out loud — rather than the internal status. An order id you were not given here will be refused: never pass one a customer read out, one from an earlier conversation, or one you produced yourself.JhaCommerceJhaXPluginnoneCommerce
Check payment statusget · Check whether the customer has paid a card checkout yet. Use this INSTEAD of get_order_status until the status is PAID — on the card path there is no order, and no orderId, until payment succeeds. ALSO SEND checkoutTrackingToken if the placement returned one. Card payment takes minutes and the connection may be re-established while the customer pays; without the token the checkout becomes unreadable at exactly that point. When the status turns PAID the reply carries orderTrackingToken — keep that one for get_order_status. AWAITING_PAYMENT: keep waiting, and re-send the link if they lost it. PAID: it carries order.orderId — only now may you say the order is placed, and from here on use get_order_status. EXPIRED or CANCELLED: NOTHING WAS CHARGED — say so plainly and offer to set it up again. Poll every few seconds while they are paying, and stop once the status is PAID, EXPIRED or CANCELLED, or once expiresAt has passed. The status is authoritative: never conclude payment from the customer saying they paid.JhaCommerceJhaXPluginnoneCommerce
Find restaurants nearbyfind · Find restaurants near a location, closest first. Distances are straight-line miles, never driving time. Pass q to return only restaurants serving a matching dish (for example 'burger'); omit q to list every nearby restaurant. LOCATION IS REQUIRED. Send lat and lng together — these come from the customer's device location, which the application supplies. Never invent or recall coordinates yourself. If you have no coordinates, send near with a city or ZIP the customer gave you; that path is not enabled on every deployment, and if the tool reports it unavailable, stop using it. radiusMiles is YOUR choice: 1-2 in a dense city, 5-10 in suburbs, up to 30 rural (30 is the cap). The server NEVER widens a radius on its own — an empty result is a correct answer to what you asked. Offer to look further out and search again. Prices are BASE prices, excluding tax and any active discount.JhaCommerceJhaXPluginnoneCommerce
Get a restaurant menuget · Get one restaurant's full menu, by category, using a restaurantId from a previous search. Prices here are EXACT — active discounts are applied — though they still exclude tax. CALL THIS WHEN YOU NEED THE MENU: the customer asks to see it, you need a category, or you need an item's modifier options. You do NOT need it before every quote. A menuItemId and price that came back from search_menu in THIS conversation are already the right ones for that restaurant, and quote_order is the authoritative total either way — so a customer who has already named their restaurant, their item and a quantity can go straight to quote_order. A LARGE MENU COMES BACK REDUCED. Restaurants here run to ~300 items, and every option of every optional modifier group is far more than one reply can carry, so detail is dropped until it fits — ids, names and exact prices ALWAYS survive, and data.detail says which level you got. For ONE item's full modifier options, call this again with menuItemId. For one section in detail, call it with category. A PRICE OF 0 IS THE RESTAURANT'S OWN FIGURE. Never replace it with a guess, a remembered price, or a price from another restaurant. Tell the customer the item is showing as free and confirm before ordering it. These are still per-item prices, not a total: once the customer has chosen their items, call quote_order for the exact amount payable. Answer every modifier group marked required before building the basket — when an index entry says has_required_modifiers, fetch that one item with menuItemId to get its option ids. JHACOMMERCE IS THE ONLY SOURCE OF RESTAURANT, MENU AND ORDER DATA HERE. Restaurants, counts, dishes and prices from any other tool, app or connector are NOT JhaCommerce data: never present them as JhaCommerce results, never blend them into a JhaCommerce list, and never use them to decide what JhaCommerce has. Only a restaurant and an item that came back from a JhaCommerce tool in this conversation can be ordered.JhaCommerceJhaXPluginnoneCommerce
List restaurantslist · List EVERY restaurant available through JhaCommerce, with its exact restaurantId. Takes no arguments and needs no location. THIS IS THE TOOL FOR ANY QUESTION ABOUT WHICH RESTAURANTS EXIST: 'how many restaurants are available?', 'what restaurants do you have?', 'which restaurants are on JhaCommerce?', 'is Rossini's available?', or when you need a restaurant's id and only have its name. Call it and answer from the result — never from memory, never from another connector, and never by guessing. THE COUNT COMES FROM restaurantCount in the reply, which is the backend's own figure. State that number and no other. For 'is <name> available?', look for that name in this result: if it is there, say so and keep its restaurantId; if it is not, say plainly that it is not one of the restaurants available here. Each entry carries the restaurant's address, phone, open state and today's hours. It carries NO menu items — call search_menu for a dish across all restaurants, or get_restaurant_menu once the customer has chosen one. JHACOMMERCE IS THE ONLY SOURCE OF RESTAURANT, MENU AND ORDER DATA HERE. Restaurants, counts, dishes and prices from any other tool, app or connector are NOT JhaCommerce data: never present them as JhaCommerce results, never blend them into a JhaCommerce list, and never use them to decide what JhaCommerce has. Only a restaurant and an item that came back from a JhaCommerce tool in this conversation can be ordered.JhaCommerceJhaXPluginnoneCommerce
Place the orderplace · Place an order. Only call this after quote_order has priced the SAME basket and the customer has confirmed that exact total — an unquoted basket is refused. SEND the quoteTrackingToken from that quote. It is what keeps the basket placeable if the connection was re-established in between, for cash and card alike. CASH (the default): the order goes to the kitchen IMMEDIATELY and may be cooking seconds later. It is not a draft and there is no cancel tool, so never place one the customer has not explicitly confirmed. You get an orderId back; track it with get_order_status. CARD: you must ask for the customer's email FIRST — the order cannot be placed without one. What comes back is a PAYMENT LINK, NOT AN ORDER: nothing has reached the kitchen and there is no orderId. Give the customer checkout.url, say the order is reserved until they pay, and tell them when the link expires. NEVER say the order is placed, confirmed or being prepared at this point. Then poll get_checkout_status. Do not call this twice for the same basket. On the card path a repeat invalidates the link the customer is already holding — use get_checkout_status instead. You never handle card details. The customer enters those on the payment page; never ask for, accept or repeat a card number, expiry or security code.JhaCommerceJhaXPluginnoneCommerce
Price an orderquote · Price a basket EXACTLY, including tax. Writes nothing — no order, no payment link, no charge. ALWAYS call this and read the total back to the customer before placing anything. You cannot work the total out yourself: tax is added by the restaurant's system and happy-hour discounts are invisible to search. NEVER state a total that did not come from this tool. Build the basket from ids the catalog returned — menuItemId, variantId and optionId exactly as given, never a name and never a price. All items must be from the SAME restaurant. Any modifier group marked required must be answered. Re-quote whenever the basket changes; it is free and it does not count against the customer's daily order limit. A basket must be quoted here before place_order will accept it. KEEP the quoteTrackingToken this returns and pass it to place_order. Without it a placement is refused if the connection was re-established between the two calls. If you no longer have it, just quote again. warnings are advisory, not failures — a closed restaurant still takes the order. Pass them on and let the customer decide.JhaCommerceJhaXPluginnoneCommerce
Search dishessearch · Search DISH and MENU-ITEM names across ALL listed restaurants, for example 'burger' or 'paneer wrap'. Returns each matching restaurant with its matching menu items, base prices, and the exact backend identifiers. IT DOES NOT SEARCH RESTAURANT NAMES. Passing a restaurant name such as 'Knowlwood' or 'Rajwadu' matches no dish and returns zero results even when that restaurant is listed and open. To find out whether a restaurant is here, search for a DISH and read the restaurant names in the result. A ZERO-RESULT SEARCH MEANS NO DISH MATCHED. It is never evidence that a restaurant does not exist, is unavailable, or has stopped trading. Never tell a customer a restaurant is unavailable on the strength of an empty search — say that nothing matched the dish, and offer to search for something else. EVERY menuItemId BELONGS TO ONE RESTAURANT. This searches every restaurant at once, so the SAME dish name comes back several times with a DIFFERENT id each time — one per restaurant, often at the same price. Once the customer picks a restaurant, use only the ids listed under THAT restaurant in this result, or call get_restaurant_menu for it and take them from there. An id from one restaurant sent with another's restaurantId is rejected; the dish is not missing, the id is simply from somewhere else. A NAMED DISH BELONGS HERE, WHETHER OR NOT YOU HAVE A LOCATION. 'I want a burger', 'I want a sandwich', 'something spicy' — call this tool with the dish. Holding the customer's location is not a reason to use find_restaurants_nearby instead; that tool is for a customer who asks for somewhere NEAR them or asks about distance, and only when a real location is available. RESULTS ARE CATALOG-WIDE AND NOT FILTERED BY PLACE. This tool takes no location and applies none. A city or ZIP the customer mentioned changes nothing about what comes back, so never describe the result as restaurants 'in' that place: 'a burger in Ahmedabad' returns burgers everywhere, not burgers in Ahmedabad. Say where a restaurant is only from its own address, and call a result location-filtered only when the result itself reports one. Prices are BASE prices, not a final payable total: they exclude tax and any active discount. Never present one as the amount the customer will pay — call get_restaurant_menu for exact prices once they pick a restaurant. After showing the matches, ask the customer which restaurant they would like, then call get_restaurant_menu for its exact prices. Price the basket with quote_order before saying any total. JHACOMMERCE IS THE ONLY SOURCE OF RESTAURANT, MENU AND ORDER DATA HERE. Restaurants, counts, dishes and prices from any other tool, app or connector are NOT JhaCommerce data: never present them as JhaCommerce results, never blend them into a JhaCommerce list, and never use them to decide what JhaCommerce has. Only a restaurant and an item that came back from a JhaCommerce tool in this conversation can be ordered.JhaCommerceJhaXPluginnoneCommerce
Get conversation activityget · Summarize one organization-owned Supovia conversation using safe status fields and sender-category counts from at most 50 recent records. No message body, preview, message id, customer identifier, staff id, internal note, organization id, or arbitrary metadata is returned.Supovia helpdesk chatSupoviaPluginrequiredCustomer Support
Get unresolved conversation countsget · Count every unresolved conversation in the authenticated Supovia organization, grouped by website. Totals cover all returned count groups; the sorted per-website preview is capped at 100 and reports truncation. Customer identifiers, staff ids, message text, and organization ids are never returned.Supovia helpdesk chatSupoviaPluginrequiredCustomer Support

Tool Explorer FAQ

What is Tool Explorer?

Tool Explorer indexes the callable tool names and descriptions attached to public registry profiles. It is useful for seeing what agents can actually invoke, not just which profile exists.

How do category and verb filters work?

Category filters use the live registry category rollup. Verb filters use the public tool insights rollup, so the page stays backed by the same read models as the tracker charts.

Why do auth requirements matter?

Auth requirements show whether a tool is likely usable without account connection, requires authentication, is private, or is unknown in the current snapshot.