AgentWeb MCP server

Tools provided by AgentWeb 37

Some details were sanitized for public display.

• agent_favoritesNo outputSchema

  Get this agent's implicit favorites: businesses it interacted with more than once, by frequency.

  Input limit?: number

  • limit?: numberoptional

    Max favorites (default: 20, max: 100)

• agent_historyNo outputSchema

  Retrieve this agent's interaction history: every business it searched for, viewed, or contributed to. Persists 90 days, up to 500 interactions. Recall past lookups without re-searching.

  Input limit?: number, offset?: number

  • limit?: numberoptional

    Max entries (default: 50, max: 500)

  • offset?: numberoptional

    Skip N entries (default: 0)

• agent_profileNo outputSchema

  Get this agent's identity and stats: API key info, tier, contribution count, request totals, remembered interactions.

  Input No parameters

• agentweb_capabilitiesNo outputSchema

  Get the machine-readable description of the entire AgentWeb API: every endpoint, tool, data source, and current live counts. Use to discover what AgentWeb can do.

  Input No parameters

• agentweb_get_shortNo outputSchema

  Fetch a business in the AgentWeb compact shorthand format (~320 bytes vs 3-5 KB). Single-letter keys (n=name, p=phone, e=email, w=website, h=hours, g=[lat,lng]…). ~80% fewer tokens. Use when you just need contact info. Schema: [REDACTED URI]

  Input id: string

  • id: stringrequired

    The unique business ID from AgentWeb

• agentweb_healthNo outputSchema

  Check the health status of the AgentWeb API, including total businesses and countries available.

  Input No parameters

• agentweb_leaderboardNo outputSchema

  Get the public leaderboard of top contributing AI agents (most creates, enrichments, reports).

  Input limit?: number

  • limit?: numberoptional

    Number of top contributors (default: 10, max: 50)

• batch_get_businessesNo outputSchema

  Fetch up to 50 businesses in a single call by IDs or slugs. Saves N round-trips. Supports prose (markdown), JSON, and shorthand formats.

  Input format?: string, ids: string

  • format?: stringoptional

    'text' (default) markdown; 'json' structured; 'short' compact shorthand.

  • ids: stringrequired

    Comma-separated business IDs or slugs (max 50)

• contribute_businessNo outputSchema

  Contribute a new business to AgentWeb, OR enrich an existing one with missing data (phone, email, website, hours, address). Deduplicates automatically: same name within 100m, or a matching phone, merges into the existing record. Use whenever you find structured business data AgentWeb doesn't have yet.

  Input address?: object, category?: string, country_code?: string, email?: string, hours?: object, lat?: number, lng?: number, name: string, phone?: string, website?: string

  • address?: objectoptional

    Address fields: { street, city, postcode, country, full }

  • category?: stringoptional

    Business category, e.g. 'restaurant', 'dentist', 'hotel'

  • country_code?: stringoptional

    ISO 3166-1 alpha-2 country code, e.g. 'US', 'DE'

  • email?: stringoptional

    Business email address

  • hours?: objectoptional

    Opening hours (e.g. { monday: '09:00-17:00', ... })

  • lat?: numberoptional

    Latitude (recommended for accurate dedup)

  • lng?: numberoptional

    Longitude (recommended for accurate dedup)

  • name: stringrequired

    Business name (required, min 2 chars)

  • phone?: stringoptional

    Phone number (any format; will be cleaned)

  • website?: stringoptional

    Business website URL

• currency_convertNo outputSchema

  Convert between currencies using live ECB exchange rates. 30+ currencies. Returns converted amount and rate. ~0.5s.

  Input amount: number, from: string, to: string

  • amount: numberrequired

    Amount to convert

  • from: stringrequired

    Source currency code (e.g. 'USD', 'EUR')

  • to: stringrequired

    Target currency code (e.g. 'EUR', 'JPY')

• evidence_getNo outputSchema

  Retrieve an exact evidence passage and its immutable capture metadata. Evidence is scoped to this application's user/workspace and retained for seven days.

  Input evidence_id: string

  • evidence_id: stringrequired
• execute_recipeNo outputSchema

  Execute a public recipe discovered with list_recipes. Pass its exact domain, recipe_name and named params. Covers all public recipes, including those without a dedicated tool. Upstream errors are returned as tool errors. Authentication follows the selected recipe.

  Input domain: string, params: object, recipe_name: string

  • domain: stringrequired

    Catalog key, e.g. news, holidays, wikipedia.org or amazon.com

  • params: objectrequired

    Named parameters from list_recipes. Do not include authentication credentials.

  • recipe_name: stringrequired

    Recipe name, e.g. search, list or search_products

• flixbus_searchNo outputSchema

  Search FlixBus bus and train routes between cities in Europe. Returns prices, times, duration, transfers, booking links. ~1s.

  Input adults?: number, date: string, from: string, limit?: number, sort?: string, to: string

  • adults?: numberoptional

    Passengers (default: 1)

  • date: stringrequired

    Travel date YYYY-MM-DD

  • from: stringrequired

    Origin city (e.g. 'Copenhagen', 'Berlin')

  • limit?: numberoptional

    Max results (default: 10)

  • sort?: stringoptional

    Sort (default: cheapest)

  • to: stringrequired

    Destination city (e.g. 'Berlin', 'Rome')

• get_businessNo outputSchema

  Fetch a single business by slug or UUID. Returns markdown prose by default (~60% fewer tokens than JSON). Slugs look like 'noma-copenhagen-abc12345'. Use when you already have an identifier from a previous search. Set format='json' for structured data.

  Input format?: string, id: string

  • format?: stringoptional

    'text' (default) markdown prose; 'json' structured JSON.

  • id: stringrequired

    Business slug (e.g. 'noma-copenhagen-abc12345') or UUID. Slugs preferred.

• kiwi_search_flightsNo outputSchema

  Search flights on Kiwi.com: aggregates all airlines, often cheaper than airline sites. Returns prices, airlines, times, stops, duration, booking links. ~1.5s.

  Input adults?: number, cabin?: string, depart: string, from: string, limit?: number, return?: string, sort?: string, to: string

  • adults?: numberoptional

    Adult passengers (default: 1)

  • cabin?: stringoptional

    Cabin class (default: ECONOMY)

  • depart: stringrequired

    Departure date YYYY-MM-DD

  • from: stringrequired

    Origin airport IATA code

  • limit?: numberoptional

    Max results (default: 10)

  • return?: stringoptional

    Return date YYYY-MM-DD (omit for one-way)

  • sort?: stringoptional

    Sort (default: price)

  • to: stringrequired

    Destination airport IATA code

• list_recipesNo outputSchema

  Discover every public recipe and its parameters, authentication and cache policy. Includes news, holidays, Wikipedia, Amazon products and provider-specific travel. A listed recipe is not a guarantee of upstream availability.

  Input No parameters

• local_searchNo outputSchema

  Search local businesses from external sources; availability and freshness vary. Returns name, star rating, review count, phone, today's opening hours, website, full address, category, and geo coordinates for each result. Use when you need CURRENT info (today's hours, latest ratings) or when search_businesses doesn't have the business yet. Use for location-based business queries. Results may be cached.

  Input limit?: number, location?: string, query: string

  • limit?: numberoptional

    Maximum number of results (default: 15)

  • location?: stringoptional

    City, area, or 'near me': e.g. 'Copenhagen', 'Shibuya Tokyo'

  • query: stringrequired

    What to look for, e.g. 'coffee shops', 'dentist', 'thai restaurant'

• report_businessNo outputSchema

  Report a business as closed, having wrong info, or being spam. Three or more 'closed' reports automatically lower its confidence score. Use when you discover a business is permanently closed, has wrong phone/address/hours, is spam, or is a duplicate.

  Input business_id: string, details?: string, report_type: string

  • business_id: stringrequired

    The unique business ID from AgentWeb (required)

  • details?: stringoptional

    Optional free-text explanation, max 500 chars

  • report_type: stringrequired

    Type of issue

• research_cancelNo outputSchema

  Request cancellation of an accepted research execution. In-flight usage can remain pending; retrying cancellation does not start new work.

  Input request_id: string

  • request_id: stringrequired
• research_statusNo outputSchema

  Get the status, evidence and usage receipt of an accepted research request.

  Input request_id: string

  • request_id: stringrequired
• search_attractionsNo outputSchema

  Search real-time attractions, tours, and activities on booking.com via AgentWeb. Returns name, price, description, rating, duration, free-cancellation, discounts, booking links. ~2s.

  Input date: string, destination: string, end_date?: string, limit?: number, sort?: string

  • date: stringrequired

    Date YYYY-MM-DD

  • destination: stringrequired

    City name (e.g. 'Rome', 'Tokyo', 'Barcelona')

  • end_date?: stringoptional

    End date YYYY-MM-DD (defaults to date)

  • limit?: numberoptional

    Max results (default: 15)

  • sort?: stringoptional

    Sort (default: popular)

• search_businessesNo outputSchema

  Search the AgentWeb global business directory. Use agentweb_health for current counts. If a business is not in the database yet, AgentWeb tries to discover it from the web in real time (~3s) and saves it. Returns markdown prose by default. Supports text search (q), category, city/country, and geographic search (lat+lng+radius_km). ONE CALL RETURNS EVERYTHING: name, phone, email, hours, website, address, geo, trust score. Use format='json' for structured JSON.

  Input category?: string, city?: string, country?: string, cursor?: string, format?: string, lat?: number, limit?: number, lng?: number, q?: string, radius_km?: number

  • category?: stringoptional

    Business category filter (e.g., 'restaurant', 'hotel', 'pharmacy')

  • city?: stringoptional

    City name for location filter

  • country?: stringoptional

    Country code (ISO 3166-1 alpha-2, e.g., 'US', 'GB', 'DK')

  • cursor?: stringoptional

    Pagination cursor from a previous response's meta.next_cursor

  • format?: stringoptional

    Response format. 'text' (default) returns markdown prose; 'json' returns structured JSON.

  • lat?: numberoptional

    Latitude for geographic search (requires lng and radius_km)

  • limit?: numberoptional

    Maximum number of results (default: 10, max: 100)

  • lng?: numberoptional

    Longitude for geographic search (requires lat and radius_km)

  • q?: stringoptional

    Text search query, e.g. 'noma', 'thai restaurant', 'dentist near me'

  • radius_km?: numberoptional

    Search radius in kilometers (used with lat/lng)

• search_carsNo outputSchema

  Search real-time car rental availability and prices on booking.com via AgentWeb. Returns vehicle, supplier (Avis, Hertz, Sixt…), price, transmission, doors, mileage, pickup location, booking links. Works with any airport IATA code. ~1s.

  Input driver_age?: number, dropoff?: string, dropoff_date: string, dropoff_time?: string, limit?: number, location: string, pickup_date: string, pickup_time?: string, sort?: string, transmission?: string

  • driver_age?: numberoptional

    Driver age (default: 30)

  • dropoff?: stringoptional

    Drop-off location if different from pickup

  • dropoff_date: stringrequired

    Drop-off date YYYY-MM-DD

  • dropoff_time?: stringoptional

    Drop-off time HH:MM (default: 10:00)

  • limit?: numberoptional

    Max results (default: 15)

  • location: stringrequired

    Pickup: airport IATA code or city name

  • pickup_date: stringrequired

    Pickup date YYYY-MM-DD

  • pickup_time?: stringoptional

    Pickup time HH:MM (default: 10:00)

  • sort?: stringoptional

    Sort by price

  • transmission?: stringoptional

    Filter by transmission type

• search_flightsNo outputSchema

  Search flights across multiple sources (booking.com + kiwi.com) and return the cheapest. Returns airlines, prices, times, stops, duration, source, and booking links. ~3s.

  Input adults?: number, cabin?: string, depart: string, from: string, limit?: number, return?: string, sort?: string, to: string

  • adults?: numberoptional

    Adult passengers (default: 2)

  • cabin?: stringoptional

    Cabin class (default: ECONOMY)

  • depart: stringrequired

    Departure date YYYY-MM-DD

  • from: stringrequired

    Origin airport IATA code (e.g. 'CPH', 'JFK', 'LHR')

  • limit?: numberoptional

    Max results (default: 10)

  • return?: stringoptional

    Return date YYYY-MM-DD (omit for one-way)

  • sort?: stringoptional

    Sort order

  • to: stringrequired

    Destination airport IATA code (e.g. 'FCO', 'CDG', 'NRT')

• search_hotelsNo outputSchema

  Search hotels across multiple sources (booking.com + kiwi.com) and return the cheapest. Returns name, price, stars, rating, reviews, source, booking links. ~2s.

  Input adults?: number, checkin: string, checkout: string, destination: string, limit?: number, max_price?: number, sort?: string

  • adults?: numberoptional

    Adult guests (default: 2)

  • checkin: stringrequired

    Check-in date YYYY-MM-DD

  • checkout: stringrequired

    Check-out date YYYY-MM-DD

  • destination: stringrequired

    City or destination (e.g. 'Rome', 'Tokyo')

  • limit?: numberoptional

    Max results (default: 10)

  • max_price?: numberoptional

    Maximum price per night filter

  • sort?: stringoptional

    Sort by price

• suggestNo outputSchema

  Autocomplete / type-ahead for business names, cities, or categories. Use to disambiguate user input before searching. Returns up to 15 suggestions by relevance. Fast (<20ms).

  Input country?: string, limit?: number, q: string, type?: string

  • country?: stringoptional

    Optional ISO country code to narrow suggestions

  • limit?: numberoptional

    Max suggestions (default: 10, max: 15)

  • q: stringrequired

    Query prefix, min 2 characters (e.g. 'nom', 'copenh')

  • type?: stringoptional

    What to autocomplete (default: 'business').

• time_convertNo outputSchema

  Convert a local date/time between IANA zones, supported cities or countries. Rejects nonexistent clock-change times. Repeated local times require fold=0/1 or an explicit UTC offset. HH:MM uses today's date in the source zone.

  Input fold?: integer, from: string, time?: string, to: string

  • fold?: integeroptional

    First (0) or second (1) occurrence during a backward clock change.

  • from: stringrequired

    Source IANA timezone, supported city or country.

  • time?: stringoptional

    ISO datetime, YYYY-MM-DD HH:MM, HH:MM or now (default).

  • to: stringrequired

    Destination IANA timezone, supported city or country.

• time_nowNo outputSchema

  Get the current date and time in a country (e.g. Denmark), supported city, or IANA timezone. Returns UTC offset, DST, Unix timestamp and timezone-data version. Fresh every call. Countries with multiple zones return choices; select one and retry. Use this for 'What time is it in Denmark right now?'.

  Input location?: string, timezone?: string

  • location?: stringoptional

    Country name/code or supported city, e.g. Denmark, DK, Tokyo. Use either location or timezone.

  • timezone?: stringoptional

    IANA timezone, e.g. Europe/Copenhagen. Defaults to UTC if neither field is supplied.

• trending_businessesNo outputSchema

  Get the most searched/popular businesses on AgentWeb right now (last 24h or all time).

  Input limit?: integer, period?: string

  • limit?: integeroptional

    Max results (default: 10)

  • period?: stringoptional

    Time period (default: '24h').

• watch_cancelNo outputSchema

  Cancel a watch and its queued callback deliveries. An already in-flight delivery may still arrive.

  Input watch_id: string

  • watch_id: stringrequired
• watch_createNo outputSchema

  Create an expiring, resource-limited watch for URL text changes, text appearance or an unambiguous structured product price. Baselines are silent by default. An optional webhook receives signed changes; without it, poll watch_events.

  Input currency?: any, expires_in_seconds?: integer, idempotency_key?: string, interval_seconds?: integer, kind: string, max_checks?: integer, max_pages?: integer, max_units?: integer, notify_initial?: boolean, price?: any, query?: any, terms?: array, url?: any, webhook_url?: any

  • currency?: anyoptional
  • expires_in_seconds?: integeroptional
  • idempotency_key?: stringoptional

    Reuse for a retry of exactly the same operation/input.

  • interval_seconds?: integeroptional
  • kind: stringrequired
  • max_checks?: integeroptional
  • max_pages?: integeroptional
  • max_units?: integeroptional
  • notify_initial?: booleanoptional
  • price?: anyoptional
  • query?: anyoptional
  • terms?: arrayoptional
  • url?: anyoptional
  • webhook_url?: anyoptional
• watch_eventsNo outputSchema

  Read detected changes, supporting evidence and delivery status for a watch in the current scope.

  Input after?: string, watch_id: string

  • after?: stringoptional

    next_cursor from the previous page

  • watch_id: stringrequired
• watch_listNo outputSchema

  List change watches in the current application/user/workspace scope.

  Input No parameters

• weather_forecastNo outputSchema

  Get weather forecast for any city worldwide. Returns current conditions plus daily forecast up to 14 days (high/low, rain chance, UV, sunrise/sunset, packing advisories). ~1s.

  Input city: string, days?: number, units?: string

  • city: stringrequired

    City name (e.g. 'Rome', 'Tokyo', 'New York')

  • days?: numberoptional

    Forecast days (1-14, default: 3)

  • units?: stringoptional

    Temperature unit (default: celsius)

• web_fetchNo outputSchema

  Page fetch. Fetches a public URL and returns its cleaned text content (title + body) ready to read.

  Input max_chars?: number, url: string

  • max_chars?: numberoptional

    Truncate content (default 8000)

  • url: stringrequired

    The page URL to fetch

• web_researchNo outputSchema

  Web search PLUS the cleaned text of the top pages in one call (pages are fetched in parallel). Prefer this over web_search + web_fetch whenever you need to read the results, not just list them.

  Input entity?: string, idempotency_key?: string, intent?: string, max_chars?: integer, max_duration_ms?: integer, max_units?: integer, num?: integer, q: string

  • entity?: stringoptional

    Explicit entity for official_website candidate identification; ownership is not verified.

  • idempotency_key?: stringoptional

    Reuse for a retry of exactly the same operation/input.

  • intent?: stringoptional
  • max_chars?: integeroptional

    Characters per page (default 2500)

  • max_duration_ms?: integeroptional
  • max_units?: integeroptional
  • num?: integeroptional

    Pages to read (default 3)

  • q: stringrequired

    Search query

• web_searchNo outputSchema

  General web search. mode=index searches AgentWeb's own indexed pages with a short time budget; mode=hybrid also queries external sources (the default). Returns the top web results (title, URL, snippet) for a query: general web pages, not just businesses. Use for research, finding pages, and current info. Pair with web_fetch to read a result.

  Input mode?: string, num?: integer, q: string

  • mode?: stringoptional
  • num?: integeroptional

    Number of results (default 10, max 20)

  • q: stringrequired

    Search query