AgentWeb
Server Details
Free web search, 130M+ business records, local search, weather and travel data for AI agents.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 37 tools
Most tools have distinct resource+action pairs, and the descriptions actively steer between near-neighbors (search_businesses vs local_search, search_flights vs kiwi_search_flights, web_search vs web_research vs web_fetch). The main soft spots are the agent_* introspection trio (favorites/history/profile) and the four ways to retrieve a business (get_business, agentweb_get_short, batch_get_businesses, search_businesses), which are separable but require reading the descriptions closely.
Everything is snake_case, which keeps it readable, but the convention is inconsistent: verb_noun (search_businesses, list_recipes, watch_create) mixes with noun_verb (evidence_get, research_status, research_cancel, flixbus_search, kiwi_search_flights). Prefixing is also ad hoc, with agent_, agentweb_ and unprefixed tools coexisting for closely related resources.
37 tools is heavy, but the server genuinely spans several domains (business directory, travel search, web research, watches, recipes, utilities), so each cluster is only 3-5 tools. It is still on the bloated side and a few tools (agentweb_capabilities, agentweb_health, suggest) feel like discovery/niceties rather than core operations.
Coverage is strong across the inferred domains: business discovery/enrichment/flagging, batch reads, travel search for flights/hotels/cars/attractions/buses, full watch lifecycle (create/list/events/cancel), recipe discovery+execution, research status/cancel, and conversion/time/weather utilities. Minor gaps remain, such as no way to update or delete a contributed business (only report), and no batch contribute.
Available Tools
37 toolsagent_favoritesMy favoritesARead-onlyIdempotentInspect
Get this agent's implicit favorites: businesses it interacted with more than once, by frequency.
Inputs: limit.
agent_historyMy historyARead-onlyIdempotentInspect
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.
Inputs: limit, offset.
agent_profileMy profileARead-onlyIdempotentInspect
Get this agent's identity and stats: API key info, tier, contribution count, request totals, remembered interactions.
Inputs: no named parameters.
agentweb_capabilitiesAgentWeb capabilitiesARead-onlyIdempotentInspect
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.
Inputs: no named parameters.
agentweb_get_shortGet business (short)ARead-onlyIdempotentInspect
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: https://api.agentweb.live/v1/schema/short
Inputs: id (required).
agentweb_healthAgentWeb healthARead-onlyIdempotentInspect
Check the health status of the AgentWeb API, including total businesses and countries available.
Inputs: no named parameters.
agentweb_leaderboardContributor leaderboardBRead-onlyIdempotentInspect
Get the public leaderboard of top contributing AI agents (most creates, enrichments, reports).
Inputs: limit.
batch_get_businessesGet businesses (batch)BRead-onlyIdempotentInspect
Fetch up to 50 businesses in a single call by IDs or slugs. Saves N round-trips. Supports prose (markdown), JSON, and shorthand formats.
Inputs: ids (required), format.
contribute_businessContribute businessAInspect
Add a business AgentWeb does not have, or fill the empty fields of one it has (phone, email, website, hours, category). Send the name with at least one of phone, website, email, lat and lng, or address.city. A stored business is matched by the same name within 100 m, or the same name with the same phone or website. Stored values are never replaced: the answer lists what was filled. To flag a wrong stored value, use report_business.
Inputs: name (required), lat, lng, email, +6 more.
currency_convertConvert currencyARead-onlyIdempotentInspect
Convert between currencies using live ECB exchange rates. 30+ currencies. Returns converted amount and rate. ~0.5s.
Inputs: to (required), from (required), amount (required).
evidence_getEvidence getBRead-onlyIdempotentInspect
Retrieve an exact evidence passage and its immutable capture metadata. Evidence is scoped to this application's user/workspace and retained for seven days.
Inputs: evidence_id (required).
execute_recipeExecute recipeAInspect
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.
Inputs: domain (required), params (required), recipe_name (required).
flixbus_searchSearch busesARead-onlyIdempotentInspect
Search FlixBus bus and train routes between cities in Europe. Returns prices, times, duration, transfers, booking links. ~1s.
Inputs: to (required), date (required), from (required), sort, +2 more.
get_businessGet businessARead-onlyIdempotentInspect
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.
Inputs: id (required), format.
kiwi_search_flightsSearch flights (Kiwi)ARead-onlyIdempotentInspect
Search flights on Kiwi.com: aggregates all airlines, often cheaper than airline sites. Returns prices, airlines, times, stops, duration, booking links. ~1.5s.
Inputs: to (required), from (required), depart (required), sort, +4 more.
list_recipesList recipesARead-onlyIdempotentInspect
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.
Inputs: no named parameters.
local_searchLive local searchAInspect
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.
Inputs: query (required), limit, location.
report_businessReport businessAInspect
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.
Inputs: business_id (required), report_type (required), details.
research_cancelResearch cancelBInspect
Request cancellation of an accepted research execution. In-flight usage can remain pending; retrying cancellation does not start new work.
Inputs: request_id (required).
research_statusResearch statusBRead-onlyIdempotentInspect
Get the pages read so far for a web_research request that was still running, by its request_id.
Inputs: request_id (required), format.
search_attractionsSearch attractionsARead-onlyIdempotentInspect
Search real-time attractions, tours, and activities on booking.com via AgentWeb. Returns name, price, description, rating, duration, free-cancellation, discounts, booking links. ~2s.
Inputs: date (required), destination (required), sort, limit, +1 more.
search_businessesSearch businessesAInspect
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.
Inputs: q, lat, lng, city, +6 more.
search_carsSearch car rentalsARead-onlyIdempotentInspect
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. Takes an airport IATA code or a city name. ~1s.
Inputs: location (required), pickup_date (required), dropoff_date (required), sort, +6 more.
search_flightsSearch flightsARead-onlyIdempotentInspect
Search flights across multiple sources (booking.com + kiwi.com) and return the cheapest. Returns airlines, prices, times, stops, duration, source, and booking links. ~3s.
Inputs: to (required), from (required), depart (required), sort, +4 more.
search_hotelsSearch hotelsARead-onlyIdempotentInspect
Search hotels across multiple sources (booking.com + kiwi.com) and return the cheapest. Returns name, price, stars, rating, reviews, source, booking links. ~2s.
Inputs: checkin (required), checkout (required), destination (required), sort, +3 more.
suggestAutocompleteARead-onlyIdempotentInspect
Complete the start of a business name, city or category. Use it to find the exact spelling before searching. Business names come in alphabetical order, cities largest first, categories by number of businesses.
Inputs: q (required), type, limit, country.
time_convertConvert timeARead-onlyIdempotentInspect
Convert a date and time between two places. Each place is a country, city, IANA timezone, abbreviation (EST) or offset (UTC+1). A clock time alone means today in the source place. A time that is skipped or repeated at a clock change is explained in the error.
Inputs: to (required), from (required), fold, time.
time_nowCurrent local timeARead-onlyIdempotentInspect
Get the current date and time for a place: a country (Denmark), city (Tokyo), IANA timezone (Europe/Copenhagen), abbreviation (EST) or offset (UTC+1). Returns local time, weekday, UTC offset and DST. Fresh every call. A place with several clocks returns candidates: pick one and call again. Use this for 'What time is it in Denmark right now?'.
Inputs: location, timezone.
trending_businessesTrending businessesARead-onlyIdempotentInspect
Get the most searched/popular businesses on AgentWeb right now (last 24h or all time).
Inputs: limit, period.
watch_cancelWatch cancelAInspect
Cancel a watch and its queued callback deliveries. An already in-flight delivery may still arrive.
Inputs: watch_id (required).
watch_createWatch createAInspect
Watch a web page and report when it changes. Give url and kind. kind=content_changed: the page text changed. kind=text_appeared: one of terms shows up (works with url, or with query to watch search results). kind=price_below: the product price falls under price (needs price and currency). kind=price_dropped: the price falls below the last one seen (needs currency, no price). The first check is silent. Read changes with watch_events, or give webhook_url to receive them.
Inputs: kind (required), url, price, query, +10 more.
watch_eventsWatch eventsBRead-onlyIdempotentInspect
Read detected changes, supporting evidence and delivery status for a watch in the current scope.
Inputs: watch_id (required), after.
watch_listWatch listARead-onlyIdempotentInspect
List change watches in the current application/user/workspace scope.
Inputs: no named parameters.
weather_forecastWeather forecastARead-onlyIdempotentInspect
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.
Inputs: city (required), days, units.
web_fetchFetch web pageARead-onlyIdempotentInspect
Read one public web page. Returns the title and the page text from the top as plain text, and says how long the whole page is. A URL that ends in #section is read from that section. For a long page, call again with the start value the answer gives.
Inputs: url (required), start, format, max_chars.
web_researchWeb research (search + read)AInspect
Search the web and read the top pages in one call. Returns each page as plain text: title, URL and the passages that match the query. Use it when you need what the pages say, not only a list of links.
Inputs: q (required), num, entity, format, +5 more.
web_searchWeb searchARead-onlyIdempotentInspect
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 as a short numbered list: general web pages, not just businesses. Use for research, finding pages, and current info. Add site:docs.python.org to the query to search one site. Pair with web_fetch to read a result.
Inputs: q (required), num, mode, format, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Paid web research, news, company briefs, fact-checks and US weather data for AI agents
The best web search for your AI Agent
Web search, browser automation, scraping, crawling and CAPTCHA solving for AI agents.
Web scraping, search, crawling, structured extraction and research for AI agents.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceWeb search, clean page reading & one-call research dossiers for AI agents. No API key — your agent does the synthesis.81 npmMIT
- AlicenseAqualityDmaintenanceEnables AI agents to perform Google searches and retrieve structured JSON results for 10 types including web, images, news, and shopping with live prices. Offers 1,000 free searches per month with no credit card required.137 npmMIT
- AlicenseBqualityDmaintenanceEnables LLMs and AI agents to access real-time web data, search websites, and navigate the web without getting blocked. Includes 5,000 free monthly requests and supports web scraping, browser automation, and bypassing geo-restrictions.6022,736 npm1MIT

Anakinofficial
AlicenseAqualityCmaintenanceWeb data for AI agents: scrape, crawl, search, deep research, site monitoring, browser automation2273 npm3Apache 2.0
Glama MCP Gateway
Add one secure layer between your agents and this server.