614,643 tools. Updated 2026-09-26 22:23
"Gin" matching MCP tools:
- Find every cocktail in the catalogue that uses one specific ingredient. Matching is a case- and diacritic-insensitive substring match against each cocktail's ingredient names, so "gin" will also match "sloe gin" and "ginger beer" — use a more specific term if that matters. Returns up to 60 summary results (name, URL, family, glassware) in catalogue order. Takes one ingredient only; for "what can I make from X, Y, and Z?" use find_makeable_cocktails instead, which handles multiple ingredients and reports near-misses.ConnectorNo auth
- Use this when the buyer explicitly asks to cancel an order placed through pinflower_create_order. The website's rules apply: free while the florist has not confirmed, and for a later-day order until the cut-off before its time window; a paid amount is refunded in full. Two steps: call with order_ref and confirm=true — a 6-digit code goes to the e-mail the order was placed with; then call again with the code the buyer reads from that e-mail. Not for changing an order — cancel and order again.ConnectorDestructiveNo auth
- Given the ingredients you have on hand, find every cocktail you can make completely — one where you already have all of its ingredients. Garnishes are treated as optional and plain water is assumed available; soda and tonic water are not. Matching is word-based, not substring: "gin" matches "London dry gin" but not "ginger beer", and generic terms do not match product-class extras ("gin" will not cover "sloe gin" or "orange bitters"). Returns two lists: "makeable" (drinks you can make now, up to 60) and "almostMakeable" (drinks exactly one ingredient short, up to 25, each naming the missing ingredient). Drinks needing two or more extra ingredients are omitted entirely. Both lists are ordered simplest first — fewest distinct ingredients in the full recipe, then alphabetical by name. Use this for multi-ingredient "what can I make?" questions; for a single ingredient use find_cocktails_by_ingredient.ConnectorNo auth
- Suggest one cocktail picked uniformly at random from the catalogue (or from one family if "family" is given) and return its full recipe — ingredients with measures, preparation steps, garnish, glassware, page URL, and any film or TV appearances. Each call returns an independent draw, so repeated calls give different drinks. The "family" filter matches the family name exactly (case- and diacritic-insensitive); if no cocktail matches that family the call silently falls back to the full catalogue rather than erroring. Use this only when the user wants a suggestion or inspiration with no specific drink in mind. For a named cocktail use get_cocktail_recipe; for "anything with gin" use find_cocktails_by_ingredient; for "what can I make from what I have" use find_makeable_cocktails.ConnectorNo auth
- ACCOUNT REQUIRED (free — sign in via GitHub at https://pipeworx.io/signup; depth:"thorough" needs a paid plan). If you are not signed in, use ask_pipeworx instead — it works on every tier. Grounded multi-source research across Pipeworx's 1679 STRUCTURED data sources (SEC filings, FRED/BLS economics, FDA, USPTO patents, markets, science, government records, etc.) in ONE call — this is NOT open-web search. Decomposes your question into focused facets, routes each to the right one of 6,425 tools IN PARALLEL, and returns a findings packet: verbatim evidence + confidence + source + fetched_at + a stable pipeworx:// citation per finding, with explicit gaps[] for facets the data couldn't answer (never invented). Best for broad/multi-part questions over structured data ("compare X and Y's regulatory + financial exposure", "research the filings + market picture for ACME"). For a single lookup use ask_pipeworx (one LLM call, not many). For BREAKING or colloquial CURRENT-NEWS / "what's the world saying about X" topics, prefer ask_pipeworx — it routes to live news APIs and the *-news-feeds packs; deep_research returns mostly empty gaps[] when the topic isn't in the structured catalog. Second-hop iteration: depth:"standard" re-angles unanswered gaps (gap recovery); depth:"thorough" additionally chases the best leads from the first pass — so multi-step questions resolve in one call. Every finding carries a `hop` field and a citation_uri — a resolvable pipeworx:// record URI, present only when the source emits one that resources/read can actually serve, so a citation you get back is always fetchable. "standard" and "thorough" also return contradictions[] flagging findings that disagree. Large records are semantically excerpted to the passages relevant to each facet (not head-truncated), so answers deep in a long filing/series aren't missed. Expect 15-60s (thorough with its follow-up + contradiction pass: up to ~90s).ConnectorNo auth
- Use this when the buyer wants flowers delivered in Prague (or picked up there) and you need concrete bouquets: it returns only bouquets that can really arrive at the given place and time, with price, delivery fee, total and the earliest delivery time, in the storefront's recommended order. Pass what the buyer said: free text, occasion, budget, where, date and a deliver-by time. Do not use it for general flower advice or for orders outside Prague. Show 3–6 results; then use pinflower_get_bouquet for details or pinflower_create_order to order.ConnectorNo auth
Matching MCP Servers
- AlicenseAqualityBmaintenanceAbout The fast, idiomatic way to build MCP servers in Go. Gin-like DX with struct-tag auto schema, middleware, adapters for Gin/OpenAPI/gRPC.514Apache 2.0
- AlicenseAqualityCmaintenanceProvides AI assistants with progressive code intelligence to explore repository structure, find symbols, and assess the impact of changes using ast-grep.3MIT
Matching MCP Connectors
Reads and validates any European e-invoice a business receives — XRechnung, UBL, CII, ZUGFeRD/Factur-X PDF, Peppol BIS 3, FatturaPA, KSeF FA(3) — into canonical EN 16931 JSON with plain-language fix hints in EN/DE/PL/IT/FR, plus PDF, CSV and DATEV export. Nothing is stored; works without a key on a small daily quota.
LinkedIn data for AI agents: structured profiles, people search, companies, and posts over MCP or REST. 500 free credits, no card.
- Compute the exact Eveoy price for a pilot. Pricing mirrors eveoy.com/order. Base: customers_per_location × locations × $24.99. Optional guaranteed purchase (guarantee_type "visit_purchase"): every shopper also buys your chosen SKU at your register — add the SKU price (in cents, tax included, $5–$100) at cost, no item fee; the item money rings back into your till. Optional shopper bonus ($20–$200 per shopper, 33% platform fee on the bonus only — the only platform fee): every $20 unlocks +1 photo and +1 follow/like/comment set per shopper, each capped at +3. Total = units×2499 + units×sku + round(units×bonus×1.33) cents — the same server-side math Stripe charges. The marketing-default $999 pilot is 40 customers at 1 location, visit-only. Floor 20/location, ceiling 1,000/location, locations cap 50. Use this when the user wants to: - Get a price for a specific shopper/customer count and location count ("price 200 shoppers across 3 stores") - Quote a pilot with a guaranteed purchase and/or a shopper bonus, with the full fee breakdown - Get a budget estimate or compare cost across pilot sizes - Confirm the per-shopper rate before booking Trigger phrases include: "how much does eveoy cost", "price for 500 shoppers", "what's a pilot cost with a guaranteed purchase", "what does the bonus cost", "eveoy pricing", "quote me a pilot for 100 shoppers in 4 stores". Returns: { customers_per_location, locations, total_customers, unit_price_usd, total_usd, formatted_total, ugc_photos, is_starter_tier, guarantee_type, top_sku_price_cents, shopper_bonus_cents, fee_breakdown { base_cents, sku_cents, bonus_cents }, bonus_tiers }. Reflects the exact math the eveoy.com/order backend applies; never returns a number the form would reject. Do NOT use this for: - General "what is eveoy" questions (use ask_eveoy) - Industries served (use list_industries) - Custom volume contracts beyond the 50-location ceiling — route the buyer to support@eveoy.com Cost: free. Latency: <100ms. Read-only. Idempotent. Deterministic.ConnectorNo auth
- Return the list of industries Eveoy serves — 23+ B2C sectors across retail, food, beauty, hospitality, pets, and more. Use this when the user wants to: - Check whether Eveoy supports their vertical ("do you do coffee shops?") - See the full list of supported industries - Confirm an industry before pricing or booking a pilot Trigger phrases include: "what industries does eveoy support", "do you work with QSR", "list verticals", "is eveoy good for fitness studios", "what categories", "what sectors". Returns: { industries: string[], count: number, notes: string }. Each entry is a canonical sector name suitable for downstream use. Do NOT use this for: pricing (use get_pricing) or general Eveoy questions (use ask_eveoy). Cost: free. Latency: <100ms. Read-only. Cacheable. Deterministic.ConnectorNo auth
- ACCOUNT REQUIRED (free — sign in via GitHub at https://pipeworx.io/signup; depth:"thorough" needs a paid plan). If you are not signed in, use ask_pipeworx instead — it works on every tier. Grounded multi-source research across Pipeworx's 1675 STRUCTURED data sources (SEC filings, FRED/BLS economics, FDA, USPTO patents, markets, science, government records, etc.) in ONE call — this is NOT open-web search. Decomposes your question into focused facets, routes each to the right one of 6,404 tools IN PARALLEL, and returns a findings packet: verbatim evidence + confidence + source + fetched_at + a stable pipeworx:// citation per finding, with explicit gaps[] for facets the data couldn't answer (never invented). Best for broad/multi-part questions over structured data ("compare X and Y's regulatory + financial exposure", "research the filings + market picture for ACME"). For a single lookup use ask_pipeworx (one LLM call, not many). For BREAKING or colloquial CURRENT-NEWS / "what's the world saying about X" topics, prefer ask_pipeworx — it routes to live news APIs and the *-news-feeds packs; deep_research returns mostly empty gaps[] when the topic isn't in the structured catalog. Second-hop iteration: depth:"standard" re-angles unanswered gaps (gap recovery); depth:"thorough" additionally chases the best leads from the first pass — so multi-step questions resolve in one call. Every finding carries a `hop` field and a citation_uri — a resolvable pipeworx:// record URI, present only when the source emits one that resources/read can actually serve, so a citation you get back is always fetchable. "standard" and "thorough" also return contradictions[] flagging findings that disagree. Large records are semantically excerpted to the passages relevant to each facet (not head-truncated), so answers deep in a long filing/series aren't missed. Expect 15-60s (thorough with its follow-up + contradiction pass: up to ~90s).ConnectorNo auth
- Use this when the buyer has agreed to the total from pinflower_quote_order: it creates the order exactly like the website's checkout and returns the secure payment link on pinflower.cz. Pass the same arguments as the quote, terms_accepted=true and confirmed_total_czk = the total the buyer agreed to; if the total has changed meanwhile, nothing is created and you get the new breakdown to read back. Collect first: the bouquet(s) (bouquet_id from search; several bouquets of ONE florist with quantities in items); delivery or pickup; for delivery the street address with house number in Prague (or address_mode 'ask_recipient' when the courier should agree the address with the recipient — a surprise); the recipient's name and phone when someone else receives the flowers; the date and a time (one of the times pinflower_get_bouquet offers, or 'asap', or 'agree_with_recipient'); the buyer's name, e-mail and phone (+420…); an optional card message and note for the florist; and ask whether they have a promo code; ask whether it is a purchase for a company (IČO). Above 10 000 Kč the buyer's billing address is required. Nothing is charged here and the florist is not told until the buyer pays.ConnectorNo auth
- Answer any question about Eveoy — what it is, how the platform works, pricing rationale, the directory, industries, founders, or company background. Backed by Eveoy's live knowledge base. Use this when the user wants to: - Understand what Eveoy is or does - Learn how the verified-visit / $24.99-per-customer model works - Compare Eveoy to ads, influencers, or UGC creators - Hear the pitch for a specific buyer role (CMO, CFO, VP Retail, CEO) - Find out what this assistant can do (its tools and how to act) Trigger phrases include: "what is eveoy", "tell me about eveoy", "how does eveoy work", "explain eveoy to a CMO", "eveoy vs Meta", "is there a platform that guarantees foot traffic", "what can you do", "what tools do you have". Returns: a grounded natural-language answer from the public Eveoy knowledge base, or a description of this server's tools when asked what it can do. Do NOT use this for: an exact price (use get_pricing), the industry list (use list_industries), directory search (use search_directory), or booking (use start_checkout / book_demo). Cost: free. Latency: 1–3s. Read-only.ConnectorNo auth
- Create an Eveoy checkout and return a payment link. Pricing mirrors the order page: $24.99 per verified customer base, plus two options — a guaranteed purchase (guarantee_type "visit_purchase": every shopper buys your chosen SKU at your register; you add the SKU price in cents, tax included, $5–$100, at cost — no item fee) and a shopper bonus ($20–$200 per shopper, 33% platform fee on the bonus only — the only platform fee; every $20 = +1 photo and +1 social set per shopper, max +3 each). Omit guarantee_type for a visit-only order. The server recomputes the total — what get_pricing quotes is exactly what Stripe charges. Works for agents directly — no sign-in required. Use this when the user has decided to buy and confirmed the size: - They picked a customers-per-location count (and optionally locations, guarantee, SKU price, bonus) and want to pay - Trigger phrases: "buy a pilot", "start checkout", "place an order", "let's order 100 customers with a guaranteed purchase" Provide your_name, work_email, brand_website, and campaign_start_date (at least 14 days out) — or call capture_profile first and I will reuse your saved details, then I only need campaign_start_date. For a guaranteed purchase also provide top_sku_price_cents. Returns: { checkout_url, session_id, total, customers, guarantee_type, fee_breakdown } — pay on Stripe's hosted page; no charge until then. Do NOT use this for: price-only questions (use get_pricing), saving your company (use capture_profile), or order status (use check_order_status). Confirm the customer count, guarantee choice, and total with the user first. Cost: free to call. Latency: 2-5s. Creates a real checkout session and a CRM deal (no charge until the user pays). Confirm first.ConnectorNo auth
- Get the link to book a live Eveoy demo, and flag the request to the Eveoy team. Use this when the user wants to: - Schedule a demo or walkthrough - Talk to the Eveoy team Trigger phrases include: "book a demo", "schedule a call", "talk to sales", "get a walkthrough". Pass contact_name, work_email, and company_name when you know them (or call capture_profile first) — they prefill the booking page and let the Eveoy team know who is coming; without them the request arrives anonymous. Returns: { url } — the Eveoy demo-booking page, prefilled when contact details were provided. Do NOT use this for: pricing (use get_pricing), buying (use start_checkout), or questions (use ask_eveoy). Cost: free. Latency: under 1s. Notifies the Eveoy team that a demo was requested.ConnectorNo auth
- Create a new RationalBloks project from a JSON schema. ⚠️ CRITICAL RULES - READ BEFORE CREATING SCHEMA: 1. FLAT FORMAT (REQUIRED): ✅ CORRECT: {users: {email: {type: "string", max_length: 255}}} ❌ WRONG: {users: {fields: {email: {type: "string"}}}} DO NOT nest under 'fields' key! 2. FIELD TYPE REQUIREMENTS: • string: MUST have "max_length" (e.g., max_length: 255) • decimal: MUST have "precision" and "scale" (e.g., precision: 10, scale: 2) • datetime: Use "datetime" NOT "timestamp" • ALL fields: MUST have "type" property 3. AUTOMATIC FIELDS (DON'T define): • id (uuid, primary key) • created_at (datetime) • updated_at (datetime) 4. USER AUTHENTICATION: ❌ NEVER create "users", "customers", "employees" tables with email/password ✅ USE built-in app_users table Example: { "employee_profiles": { "user_id": {type: "uuid", foreign_key: "app_users.id", required: true}, "department": {type: "string", max_length: 100} } } 5. AUTHORIZATION: Add user_id → app_users.id to enable "only see your own data" Example: { "orders": { "user_id": {type: "uuid", foreign_key: "app_users.id"}, "total": {type: "decimal", precision: 10, scale: 2} } } 6. FIELD OPTIONS: • required: true/false • unique: true/false • default: any value • enum: ["val1", "val2"] • foreign_key: "table.id" AVAILABLE TYPES: string, text, integer, decimal, boolean, uuid, date, datetime, json, uuid_array, integer_array, text_array, float_array Array types store PostgreSQL native arrays with automatic GIN indexing: • uuid_array: UUID[] — for sets of references (e.g., tensor coordinates) • integer_array: BIGINT[] — for dimension indices, integer sets • text_array: TEXT[] — for tags, categories, label sets • float_array: DOUBLE PRECISION[] — for weight vectors, scores GIN-indexed operators: @> (contains), <@ (contained_by), && (overlaps) BACKEND ENGINE: • python (default): FastAPI backend — mature, full-featured • rust: Axum backend — faster cold starts, lower memory, high performance WORKFLOW: 1. Use get_template_schemas FIRST to see valid examples 2. Create schema following ALL rules above 3. Call this tool (optionally choose backend_type: "python" or "rust") 4. Monitor with get_job_status (2-5 min deployment) After creation, use get_job_status with returned job_id to monitor deployment. While RationalBloks is being updated, the call is refused with 'RationalBloks is being updated': call it again in a few minutes.ConnectorNo auth
- Create a new RationalBloks project from a JSON schema. ⚠️ CRITICAL RULES - READ BEFORE CREATING SCHEMA: 1. FLAT FORMAT (REQUIRED): ✅ CORRECT: {users: {email: {type: "string", max_length: 255}}} ❌ WRONG: {users: {fields: {email: {type: "string"}}}} DO NOT nest under 'fields' key! 2. FIELD TYPE REQUIREMENTS: • string: MUST have "max_length" (e.g., max_length: 255) • decimal: MUST have "precision" and "scale" (e.g., precision: 10, scale: 2) • datetime: Use "datetime" NOT "timestamp" • ALL fields: MUST have "type" property 3. AUTOMATIC FIELDS (DON'T define): • id (uuid, primary key) • created_at (datetime) • updated_at (datetime) 4. USER AUTHENTICATION: ❌ NEVER create "users", "customers", "employees" tables with email/password ✅ USE built-in app_users table Example: { "employee_profiles": { "user_id": {type: "uuid", foreign_key: "app_users.id", required: true}, "department": {type: "string", max_length: 100} } } 5. AUTHORIZATION: Add user_id → app_users.id to enable "only see your own data" Example: { "orders": { "user_id": {type: "uuid", foreign_key: "app_users.id"}, "total": {type: "decimal", precision: 10, scale: 2} } } 6. FIELD OPTIONS: • required: true/false • unique: true/false • default: any value • enum: ["val1", "val2"] • foreign_key: "table.id" AVAILABLE TYPES: string, text, integer, decimal, boolean, uuid, date, datetime, json, uuid_array, integer_array, text_array, float_array Array types store PostgreSQL native arrays with automatic GIN indexing: • uuid_array: UUID[] — for sets of references (e.g., tensor coordinates) • integer_array: BIGINT[] — for dimension indices, integer sets • text_array: TEXT[] — for tags, categories, label sets • float_array: DOUBLE PRECISION[] — for weight vectors, scores GIN-indexed operators: @> (contains), <@ (contained_by), && (overlaps) BACKEND ENGINE: • python (default): FastAPI backend — mature, full-featured • rust: Axum backend — faster cold starts, lower memory, high performance WORKFLOW: 1. Use get_template_schemas FIRST to see valid examples 2. Create schema following ALL rules above 3. Call this tool (optionally choose backend_type: "python" or "rust") 4. Monitor with get_job_status (2-5 min deployment) After creation, use get_job_status with returned job_id to monitor deployment. While RationalBloks is being updated, the call is refused with 'RationalBloks is being updated': call it again in a few minutes.ConnectorNo auth
- Full brand visibility audit across LLM-indexed sources (Brave + Exa, 10 results). Returns a visibility score (0–100), score label, top 5 citation URLs, LLM index status, and 6 actionable GEO recommendations. Costs $1.50 USDC. For a quick snapshot at $0.05 use geo_quick_check.ConnectorNo auth
- Wraps `GET /api/v/:owner/:slug`. The cheap call to make before every run: the latest version, when it was published, and the price. With `wallet_signature` it also answers what that wallet already owns and what the *next* fetch would cost it — `price_kind` is `new`, `update`, `free` or `owned`. Without one it never reveals what any address owns.ConnectorNo auth
- Sucht kostenlos nach öffentlich lesbaren Regiobrett-Einträgen: Veranstaltungen, Kultur, Kurse, Vereine und lokale Angebote in der Ostschweiz. region/category sind Slugs aus dem mitgelieferten Katalog (zum Entdecken ohne Filter suchen). eventFrom/eventTo sind inklusive Veranstaltungsdaten YYYY-MM-DD in Europe/Zurich, keine Werbelaufzeiten. Datumsfilter schliessen unbekannte und wiederkehrende Termine aus. Nur aktuell sichtbare, finanzierte und moderierte Aushänge; keine vollständige Veranstaltungsübersicht. after=nextCursor bei unveränderten Filtern liefert die nächste Seite. Keine Buchung oder privaten Daten.ConnectorNo auth
- Hallucination-resistant answer mode for high-stakes reads. Same routing as ask_pipeworx — picks the right tool from 6,425 across 1679 sources, fills arguments, fetches the data — then EXTRACTS the answer using ONLY what the tool result contains. Returns {answer, evidence (verbatim quote), confidence, source, fetched_at, refusal_reason:null} on success, OR an explicit refusal {answer:null, refusal_reason:"not_in_source"|"no_tool_match"|"tool_error"|"data_truncated"|"llm_error"} when the data doesn't directly answer. Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts (financial verdicts, legal claims, medical lookups, public statements). Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.ConnectorNo auth
- Use this when the buyer is interested in one bouquet from pinflower_search_bouquets: what is inside, its size, photos, the florist's rating, the exact price with delivery and every time it can arrive on a given day. Needs bouquet_id from a search. Not for comparing many bouquets — search does that.ConnectorNo auth
- Use this when the buyer asks what is happening with an order placed through pinflower_create_order — whether it is paid, confirmed by the florist, on the way or delivered. Needs the order_ref that pinflower_create_order returned. It changes nothing — for a new payment link use pinflower_new_pay_link, to cancel pinflower_cancel_order.ConnectorNo auth