MewCP LogoAStheTech
MCPs
Use Cases

Use cases by category

Productivity & InboxInbox, calendar, and daily flowEngineering & DevOpsShip, debug, and run on-callSales & CRMPipeline, outreach, and dealsMarketing & GrowthCampaigns, SEO, and growthSupport & SuccessTriage tickets, keep customers happyFinance & OpsClose, reconcile, and expensesCreative & ContentGenerate assets and contentPeople & HiringHiring, onboarding, and HRResearch & DataSynthesize data and insights
See all use cases
Resources
BlogsProduct updates and storiesArticlesIntegration guides and code examples
PricingDocsSign in
MewCP Logo

Infrastructure You Can Trust for Agentic Products

X

Categories

  • Productivity & Docs
  • Developer Tools
  • CRM & Sales
  • Finance & Commerce
  • Data & Analytics
  • Marketing & SEO
  • Search & Web
  • Communication
  • View All Servers →

Resources

  • Blog
  • Docs
  • Privacy Policy
  • Terms of Service

Blogs

  • View All Blogs →

Articles

  • View All Articles →
Browse Servers|Pricing|Contact

Browse by Category

Productivity & Docs

  • Gmail
  • Google Drive
  • YouTube
  • Google Calendar
  • Google People
  • Google Classroom
  • Notion
  • ClickUp
  • Figma
  • Google Tasks
  • Cal
  • Monday
  • Luma
  • Notion MCP
  • Mem MCP
  • Linear MCP
  • Calendly MCP
  • Consensus MCP
  • Craft MCP
  • Close MCP
+ 23 more
  • Dice MCP
  • Lumin PDF MCP
  • Develop21 MCP
  • Granola MCP
  • Lucid MCP
  • Mermaid Chart MCP
  • Fireflies MCP
  • ClickUp MCP
  • Miro MCP
  • Llamaindex MCP
  • Otter MCP
  • Mobbin MCP
  • Descript MCP
  • ToDoist MCP
  • SlidesGPT MCP
  • AgileHero MCP
  • JobYap MCP
  • AccountHub MCP
  • Slicktrip MCP
  • Gemina MCP
  • QrVerloz
  • Tempreon MCP
  • HyperFrames MCP

Developer Tools

  • Gemini
  • Veo
  • ClickUp
  • Firecrawl
  • Vercel
  • Apify
  • Github
  • Chef
  • Scientific Calculator
  • Figma
  • HTTP
  • Perplexity
  • Apify MCP
  • Hugging Face Hub MCP
  • Buildkite MCP
  • Cloudflare MCP
  • Context7 MCP
  • Ahrefs MCP
  • Sentry MCP
  • Brevo Docs MCP
+ 54 more
  • X Docs MCP
  • Jev
  • Linear MCP
  • Calendly MCP
  • Craft MCP
  • DeepWiki MCP
  • Inspo MCP
  • Kernel MCP
  • Malwarebytes MCP
  • Mermaid Chart MCP
  • Supabase MCP
  • Microsoft Learn MCP
  • Webflow MCP
  • Scalar Docs MCP
  • Oneuptime MCP
  • Redocly MCP
  • Reducto Docs MCP
  • Llamaindex Docs MCP
  • B12 MCP
  • Lucid Docs MCP
  • Airwallex Docs MCP
  • Langfuse Docs MCP
  • Glen Docs MCP
  • AgentMail
  • Gogs Docs MCP
  • Netlify MCP
  • Neon MCP
  • Minlify Admin MCP
  • Mintlify Index MCP
  • Fern Docs MCP
  • Greptile MCP
  • Statssif Docs MCP
  • Scorecard MCP
  • Railway MCP
  • Inkbox AI
  • Stele MCP
  • LastPing MCP
  • ConsentStack
  • Iubenda MCP
  • BSV.CX MCP
  • Agent Traffic Lab MCP
  • Nippy MCP
  • Just Domain MCP
  • Grafana Cloud MCP
  • HotAPI Docs
  • Endoflife.ai MCP
  • ElevenLabs MCP
  • Laso Docs MCP
  • OpenRouter MCP
  • Replit MCP
  • Tripadvisor Docs MCP
  • GitLab MCP
  • Mailchimp Docs MCP
  • Clerk MCP

CRM & Sales

  • Google People
  • OneSignal MCP
  • Brevo Docs MCP
  • Brevo
  • Brevo MCP
  • Carbon Voice MCP
  • Clay MCP
  • Close MCP
  • Attio MCP
  • Clarify MCP
  • Hunter.io
  • Plain MCP
  • Modem MCP
  • Whats MCP

Finance & Commerce

  • Kite
  • Razorpay
  • Polymarket
  • Stripe
  • Binance
  • Upstox
  • Aiwyn MCP
  • Era-Context-MCP
  • Granted MCP
  • XDC AI MCP
  • Agentery MCP
  • Agent Embassy
  • Quick Commerce MCP
  • Longbridge MCP
  • Mercury MCP
  • Blockscout MCP
  • Octagon AI MCP
  • Stripe MCP
  • Taskrabbit MCP
  • SeatGeek MCP
+ 16 more
  • Clarity AI MCP
  • Beyond Payday MCP
  • DeFade MCP
  • MobileMRR MCP
  • SecondAppraisal MCP
  • Brek MCP
  • Coinversa Pulse MCp
  • Supermetrics Marketing Analytics MCP
  • DeepLedger MCP
  • Laso MCP
  • Laso Docs MCP
  • Razorpay MCP
  • Kiwi MCP
  • lastminute mcp
  • Coinfuty MCP
  • Pyth MCP

Data & Analytics

  • Apify MCP
  • Cloudflare MCP
  • Ahrefs MCP
  • Candid MCP
  • Consensus MCP
  • Contentsquare MCP
  • Era-Context-MCP
  • Instinct MCP
  • legal Data Hunter MCP
  • Marcopolo MCP
  • Mixpanel MCP
  • MOSPI MCP
  • Hex MCP
  • OpenRevenue MCP
  • Statsig MCP
  • Synthesize Bio MCP
  • PostHog MCP
  • PopHIVE MCP
  • Fuse Health MCP
  • Cliometry MCP
+ 5 more
  • AccuWeather MCP
  • ChEMBL MCP
  • ClinicalTrials.gov MCP
  • Staats MCP
  • NPI Registry MCP

Marketing & SEO

  • YouTube
  • Google Business
  • Mailchimp
  • Google Search Console
  • OneSignal MCP
  • Cloudflare MCP
  • Brevo Docs MCP
  • Brevo
  • Brevo MCP
  • AirOps MCP
  • Clay MCP
  • Contentsquare MCP
  • Reelsmith MCP
  • GoDaddy MCP
  • Metricool MCP
  • Webflow MCP
  • Windsor MCP
  • Commonroom MCP
  • B12 MCP
  • Hunter.io
+ 14 more
  • Get MCP Ads
  • Minlify Admin MCP
  • Zernio MCP
  • Affiliatespy MCP
  • VarynForge
  • ListingGood MCP
  • North Noir MCP
  • Supermetrics Marketing Analytics MCP
  • NitroSend MCP
  • Spicy MCP
  • Cromanion MCP
  • Manifold MCP
  • Cloro MCP
  • Agency AI MCP

Search & Web

  • Web Scrapper
  • Firecrawl
  • Apify
  • Perplexity
  • Context.dev
  • Exa
  • Brave Search
  • Apify MCP
  • Ahrefs MCP
  • DeepWiki MCP
  • Dice MCP
  • GoDaddy MCP
  • Granted MCP
  • Microsoft Learn MCP
  • Viator MCp
  • Scholargateway MCP
  • Parallel MCP
  • Mintlify Index MCP
  • OpenWeather MCP
  • Simplescraper MCP
+ 8 more
  • SearchApi MCP
  • PubMed MCP
  • YouTube Transcript AI MCP
  • AccuWeather MCP
  • bioRxiv MCP
  • HEY Research Lab MCP
  • CourtListener MCP
  • Elicit MCP

Communication

  • Gmail
  • Google Meet
  • Google Calendar
  • Mailchimp
  • WhatsApp
  • Slack
  • OneSignal MCP
  • Brevo Docs MCP
  • Carbon Voice MCP
  • Hunter.io
  • Outlook
  • Nylas MCP
  • Resend MCP
  • Read AI MCP
  • Whats MCP
  • Inkbox AI
  • QrVerloz
  • ElevenLabs MCP
  • Fathom MCP

© 2026 MewCP. All rights reserved.

  1. Home
  2. MCPs
  3. SearchApi MCP
SearchApi MCP

SearchApi MCP Integration for AI Agents

SearchApi provides real-time search and structured data retrieval across Google, Bing, Google Maps, Google Flights, Amazon, eBay, YouTube, and other platforms. Search web pages, news, products, businesses, travel options, social media content, and app store listings through a unified MCP integration.

v1.1.0107 toolsOAuth
Open in ChatGPTChatGPT
Open in ClaudeClaude
Playground
VS CodeVS Code
Connected to SearchApi MCP via MewCP.

Encrypted at rest, isolated from the model

Resolved from an AES-256-GCM vault at the moment of the call and attached to the request — the model never sees the secrets.

Try asking

Everything SearchApi MCP can do

Tools107

airbnb_experience_details

read

Get detailed information about a specific Airbnb experience by its experience ID. Returns top-level keys: `experience` (title, description, category, rating, pricing, agenda, availability, next_available_start_at_utc, location, media, highlights, things to know, accessibility features, guest requirements, cancellation policy), `host` (name, about, avatar), `reviews` (array), and `similar_experiences` (array). Use airbnb_experiences_search to find experience IDs first, then use this tool to get full details about a specific experience.

airbnb_experiences_search

read

Search Airbnb Experiences — activities, tours, and workshops hosted by locals. Returns an `experiences` array (main paginated results) and `sections` (curated thematic groups like "Get outside"; first page only). Pass `pagination.next_page_token` back as `next_page_token` to load more experiences.

airbnb_property_availability_calendar

read

Day-by-day availability calendar for a specific Airbnb property. Returns up to 12 months of data with availability, check-in/out windows, and minimum / maximum stay constraints per day. Get `property_id` from `airbnb_search` results (the `property_id` field) — the same numeric ID you'd pass to `airbnb_property`.

airbnb_property_reviews

read

Reviews for a specific Airbnb property. Returns review text, rating (1-5), date, and reviewer info. Supports filtering by text and sorting. Get `property_id` from `airbnb_search` results (the `property_id` field) — the same numeric ID you'd pass to `airbnb_property`.

airbnb_property

read

Get detailed information about a specific Airbnb property. Returns description, amenities, host info, photos, reviews, and pricing breakdown. **Two ways to look up a property:** 1. Use booking_token from airbnb_search results (recommended - preserves search context and includes pricing) 2. Use property_id with optional check_in_date/check_out_date for pricing Pricing breakdown (total price, nightly rate, fees) is only available when dates are provided via booking_token or check_in_date/check_out_date.

airbnb_search

read

Search for short-term rental properties on Airbnb. Returns listings with pricing, ratings, photos, and availability. Requires a search location or query in `q` (e.g., 'Barcelona', 'Lake Tahoe cabin'). Each result includes a booking_token for detailed property info. Use airbnb_property with booking_token to get full details including pricing breakdown.

amazon_categories

read

Browse Amazon's category hierarchy (browse nodes). Three modes: - **List roots**: call with no category_id or q to list root categories for the selected domain and category_type. - **Drill into a node**: pass category_id to return the node, its parent context, and direct children. - **Search by name**: pass q to find categories by name (case-insensitive). Use the returned `id` as the `category_id` parameter of amazon_search to filter product searches by category. category_id and q are mutually exclusive.

amazon_offers

read

Get the list of seller offers (the "Other sellers on Amazon" / All Offers Display) for an Amazon product by ASIN, including price, condition, seller, and delivery details for each offer. Use the ASIN from amazon_search results or any Amazon product URL.

amazon_product

read

Get detailed product information from Amazon by ASIN. Returns product details including title, price, description, specifications, images, and ratings. Use the ASIN from amazon_search results or any Amazon product URL.

amazon_search

read

Search for products on Amazon. Returns product listings with prices, ratings, and availability. Use amazon_product tool with the ASIN from results to get detailed product information. Use amazon_categories to discover valid category_id values for filtering by category.

apple_app_details

read

Get detailed information for an iOS or macOS app on the Apple App Store. Returns app name, description, ratings, reviews, screenshots, version history, and developer info. Required: product_id as a string of digits. Obtain it from apple_appstore_search results or from an App Store URL (the number after '/id').

apple_appstore_search

read

Search for iOS and macOS apps on the Apple App Store. Returns app listings with titles, ratings, prices, and developer info. Use apple_app_details with a product_id from results to get full app details.

apple_appstore_top_grossing

read

Get the Apple App Store top grossing chart — apps ranked by revenue for a storefront, category, and device. Returns each app's rank position, id, title, developer, category, price, and icons. No required arguments. Defaults to the top 50 grossing iPhone apps in the US storefront (country: us, category: all, store_device: iphone, num: 50). Use apple_app_details with an `id` from the results to get full app details, or apple_appstore_search to find a specific app by name.

apple_maps_guide

read

Fetch a full Apple Maps editorial guide (curated place collection): the guide's title, description, and publisher, plus every member place with full details and the guide's editorial description of it, sourced to the publisher's own article. Pass a `guide_id` from the `guide_results` of a previous apple_maps_search response. Use apple_maps_search first when you only have a topic or place name — this tool requires a guide id, not a name.

apple_maps_place_details

read

Look up full Apple Maps details for one or more places in a single request: ratings, reviews, opening hours, current open state, amenities, contact info, address, and GPS coordinates. Pass `place_id` values from a previous apple_maps_search response (up to 20, comma-separated). When at least one id resolves, identifiers Apple can't resolve are echoed back in `not_found_places`; when none resolve, the response carries an `error` instead. Use apple_maps_search first when you only have a place name — this tool requires ids, not names.

apple_maps_search

read

Search for local businesses and places on Apple Maps. Returns up to 10 local results with names, addresses, GPS coordinates, ratings, reviews, hours, phone numbers, and websites, plus a `filters` list of refinements that apply to the query. Anchor the search with `location` (a place name) or `center` (exact coordinates); results are keyed to the searched area, so an anchor is strongly recommended for local queries. Without one the search covers the whole world. To narrow results, pass `value` tokens from the `filters` array of a previous response back via the `filters` parameter. Responses may include `guide_results` (editorial guides); pass a result's `guide_id` to apple_maps_guide to fetch the full curated place list. This tool provides Apple Maps coverage, including Apple ratings, Yelp/Tripadvisor-sourced data, editorial guides, and Apple-specific filters. Google-specific place data and follow-up operations are available separately through google_maps_search, google_maps_place, and google_maps_reviews.

autoscout24_listing

read

Get the complete detail sheet for a single AutoScout24 car listing: full vehicle specification, mileage and registration, price with market context, CO2 and consumption figures, categorised equipment, accident and damage disclosure, the seller with contact phones and rating, a geo-located address, images, and the description. Pass the `link` of any autoscout24 result as `url`.

autoscout24

read

Search car listings on AutoScout24, Europe's largest online car marketplace, across eight national marketplaces. Returns listings with price, mileage, first registration, power, fuel type, transmission, seller, and location. Search is structured-filter only: there is no free-text query, so narrow with make/model and the filters below. Use autoscout24_listing with the `link` of any result to get the full vehicle detail sheet.

bestbuy_product

read

Get full BestBuy product details by SKU. Returns title, brand, model number, full specifications grouped by section, pricing with member savings and installments, ratings, reviews summary including syndicated reviews, image gallery, dimensions, and open-box pricing tiers. Requires a numeric BestBuy SKU. Use bestbuy_search first to discover SKUs by query — its `organic_results[].product_id` field is the value to pass here.

bestbuy_search

read

Search for products on BestBuy. Returns product listings with prices, ratings, reviews, images, and category taxonomy. Supports sorting, category browsing, and facet filtering.

bing_news

read

Search for news articles using Bing News. Returns news results with titles, sources, thumbnails, and publication dates. Good for finding recent news coverage and trending stories.

bing_product

read

Get detailed product information from Bing Shopping. Requires a product_token obtained from bing_shopping search results. Returns the product page with offers from multiple sellers, specifications, price history, popular opinions, and review summary.

bing_search

read

Search the web using Bing. Returns organic results, related searches and more. Alternative to Google for web search with different ranking algorithms and results.

bing_shopping

read

Search for products on Bing Shopping. Returns shopping results with titles, prices, sellers, ratings, and product_tokens. Use the product_token from a result with the bing_product tool to fetch full product page details (offers from multiple sellers, specifications, price history).

booking_autocomplete

read

Resolve a typed destination string to Booking.com's own identifiers, the entry point of the Booking chain. Returns suggestions with `title`, `label`, `dest_id`, `dest_type`, country code and coordinates, covering cities, regions, countries, districts, airports, landmarks and individual properties. Required: `q`. Use it to disambiguate a destination before calling `booking`, then pass the chosen suggestion's `dest_id` AND `dest_type` together — `booking` rejects one without the other with a 400. A `hotel` suggestion makes `booking` search that property's area with it ranked first; to read a single property, use `booking_property` with its URL instead.

booking_property

read

Full details for one Booking.com property: description, address, facilities, photos, house rules, review scores and nearby places, plus the bookable rooms with their live rates. Required: `url` — the property page URL, taken from `properties[].link` of a `booking` result. There is no id parameter; pass the URL through unchanged. The `rooms` array is only returned when `check_in_date` and `check_out_date` are both supplied, since Booking prices a stay rather than a date. Without them the response carries static property details only.

booking

read

Search Booking.com for hotels, apartments, hostels and other stays. Returns properties with price, rating, review count, room type and distance from centre, plus the available `filters` and `pagination`. Required: `q` (destination text), or `dest_id` and `dest_type` together — one without the other is rejected with a 400. Get that pair from `booking_autocomplete` when the destination is ambiguous. Prices are only returned when a stay is specified: either `check_in_date` + `check_out_date` together, or `flex_months` + `flex_stay_length` for a whole-month search. The two date modes cannot be combined, and a flexible search cannot be paginated. Each result's `link` is the property URL that `booking_property` takes to get full details, rooms and live rates.

chatgpt

read

Ask OpenAI's ChatGPT a question and get its synthesized text answer. Best for explanations, summaries, reasoning, and drafting rather than raw search-result lists. Set web_search to true to let ChatGPT browse the live web and return cited sources with the answer. Set expand_entities to true to enrich the knowledge-entity cards in the answer with rich detail cards.

duckduckgo_search_light

read

Search the web using DuckDuckGo. Returns organic results. Privacy-focused alternative to Google with unbiased results and no tracking.

ebay_product

read

Get detailed information about a specific eBay listing. Requires either an item_id or product_id obtained from ebay_search results. Returns full listing details including description, seller info, pricing, shipping options, and item specifics.

ebay_search

read

Search for listings on eBay. Returns product listings with prices, conditions, shipping info, and seller details. Use ebay_product with item_id or product_id from results to get full listing details.

ebay_shipping_calculator

read

Quote the postage a seller would pay to ship a package on eBay, from eBay's shipping rate calculator. Returns every service eBay quotes (carrier, eBay-discounted price, carrier retail price, delivery window in hours, tracking, included coverage), in eBay's order rather than sorted by price. Required: weight, length, width, height, ship_from_zip. Omit ship_to_country for a domestic quote, or set it for international services. On a domestic quote, omitting ship_to_zip returns an estimate range instead of a single price for services whose price depends on the destination. On ebay.co.uk, a quote without ship_to_zip is priced for mainland UK. These are seller-side rates. For the shipping a buyer pays on a specific listing, use ebay_product with delivery_country instead.

facebook_business_page_reviews

read

Fetch public reviews from a Facebook business page. Returns the page itself (name, link, follower counts, photos, the percentage of visitors who recommend it, and the total number of reviews) followed by each review's author, rating (recommended / not recommended), text, and timestamp, plus a pagination token for the next page. Provide exactly one of page_id, username, or url — prefer url when the user pasted any Facebook link (including mobile share links), since the tool resolves the canonical page automatically. For the second and later pages, pass the next_page_token from the previous response instead of an identifier; those pages return reviews only, with no page block.

facebook_business_page

read

Fetch public business page information from Facebook. Returns page details including name, category, address, phone, website, ratings, reviews, followers, and cover/profile photos. Provide exactly one of page_id, username, or url — prefer url when the user pasted any Facebook link (including mobile share links), since the tool resolves the canonical page automatically.

gemini

read

Get Google Gemini's AI-generated answer to a question. Returns AI-synthesized text with cited grounding source reference links.

github_search

read

Search GitHub. GitHub's qualifiers work inside q (e.g. `language:ruby stars:>1000`, `org:rails is:open`, `user:torvalds`). Required: q. Pick the vertical with type (default: repositories): - repositories: stars, language, topics, owner, issue counts - users: profiles with followers, repo count, bio, location - issues / pull_requests: title, state, labels, comments, author, repo - commits: sha, message, authors, signature verification, CI checks - topics: topic pages with repository and stargazer counts - discussions: threads with author and comment counts - packages: registry packages with downloads and latest version - wikis: wiki pages with filename and matched body text - marketplace: Apps/Actions listings, plus GitHub Models with task and token limits Valid sort values depend on type (see the sort parameter); an unsupported pairing is rejected, not ignored. Omit sort for best-match ranking. Only the first 1,000 results are reachable (10 per page, pages 1-100). Code search is not available.

google_ads_advertiser_search

read

Search for advertisers by name in Google's Ads Transparency Center. Returns advertiser IDs and domains that you can use with google_ads_search to find their ads. Requires the advertiser name to search for in `q`.

google_ads_search

read

Search for ads in Google's Ads Transparency Center by advertiser ID or domain. Returns ad creatives, formats, and targeting information. You must provide either `advertiser_id` or `domain` (at least one is required). Use advertiser_id for specific advertisers (from google_ads_advertiser_search) or domain for all ads linking to a website.

google_ai_mode

read

Get Google's AI-generated responses (AI Overviews) with source citations and reference links. Two ways to call: - Text search — requires q. - Image analysis — requires url; optionally include q to ask a question about the image. To ask a follow-up, pass the conversation_token from the previous response along with the next question in q. The answer then keeps the context of the earlier turns.

google_flights_calendar_one_way

read

Get a price calendar showing the cheapest one-way flight price for each day in a date range. Returns a list of dates with prices - useful for finding the cheapest departure day when you have flexible travel dates. For round-trip price calendars (outbound x return date grid), use google_flights_calendar_round_trip instead.

google_flights_calendar_round_trip

read

Get a price calendar showing the cheapest round-trip flight prices for combinations of outbound and return dates. Returns a grid of date pairs with prices - useful for finding the best travel window when both departure and return dates are flexible. For one-way price calendars, use google_flights_calendar_one_way instead.

google_flights_deals

read

Discover cheap round-trip flight deals from an origin, ranked by savings vs the typical price. Use for budget-friendly destination ideas, not a specific route. Required: departure_id. Each deal includes destination `name`, `kgmid`, `country`, dates, `price`, `typical_price`, savings, airline, and a `booking_link`. Defaults to the cheapest deals to anywhere. Narrow it EITHER with a free-text `q` prompt (Google's AI curates destinations, e.g. "beaches and islands") OR with `travel_class`, `stops`, `max_price`, `included_airlines`. Never both: `q` with a filter, or with a passenger count above its default, is rejected. Passengers affect pricing only alongside a filter. Origin-only: no arrival_id, and dates cannot be requested — each deal returns its own cheapest dates. **Chain handoffs:** - For dated options, pass a destination `kgmid` as `arrival_id` to `google_travel_explore_destination` or `google_flights_round_trip`. - For hotels, pass the destination `name` (NOT kgmid) as `q` to `google_hotels`.

google_flights_location_search

read

Search for airports and cities to get their identifiers for Google Flights tools. Returns: - IATA airport codes (e.g., 'JFK') for specific airports - kgmid (e.g., '/m/02_286') for cities - searches all airports in that city Required: q (location name), e.g. {"q":"Chicago"}. Use this tool when you have a city name like 'New York' or 'Paris' and need to convert it to codes that the flight tools accept. Note: Common IATA codes like JFK, LAX, SFO, LHR, CDG, NRT can be used directly without this tool.

google_flights_one_way

read

Search one-way Google Flights with airline, time, price, and booking details. Required on every call, including token follow-ups: departure_id, arrival_id, outbound_date. Preserve all original search options, including travel_class, passenger counts, currency, and filters. **Workflow:** 1. Search for flight options. 2. Repeat the arguments with the chosen flight's booking_token to retrieve booking details. Round-trip: google_flights_round_trip. Flexible dates: google_flights_calendar_one_way.

google_flights_round_trip

read

Search round-trip Google Flights with airline, time, price, and booking details. Required on every call, including token follow-ups: departure_id, arrival_id, outbound_date, return_date. Preserve all original search options, including travel_class, passenger counts, currency, and filters. **Workflow:** 1. Search for outbound flights. 2. Repeat the arguments with the chosen outbound flight's departure_token to retrieve return options. 3. Repeat the arguments, replacing departure_token with the chosen return flight's booking_token to retrieve booking details. One-way: google_flights_one_way. Flexible dates: google_flights_calendar_round_trip.

google_hotels_autocomplete

read

Autocomplete destinations and properties for hotel searches. Use to disambiguate user-typed location strings before calling `google_hotels`. Returns suggestions with `title` and `type` (destination vs property). Note: `google_hotels` accepts free-text destination names (NOT kgmid). Pass the autocomplete suggestion's `title` as the `q` parameter to `google_hotels`.

google_hotels_property

read

Detailed information about a specific hotel or vacation rental from Google Hotels — name, address, amenities, photos, reviews, ratings, and pricing for the given date range. Requires a `property_token` from `google_hotels` results (opaque, pass through).

google_hotels

read

Search for hotels using Google Hotels. Provides pricing, ratings, amenities, and availability for hotels, resorts, inns, motels, and other traditional accommodations worldwide. Required: q (destination), check_in_date, check_out_date (both YYYY-MM-DD). Use sort_by="lowest_price" for cheapest results. Supply children_ages as a string, e.g. "5,10".

google_images_light

read

Search Google Images for photos and visual content. Returns image results with thumbnails, source pages, and original image URLs. Useful for finding reference images, illustrations, and visual content.

google_jobs

read

Search for job listings on Google Jobs. Returns job postings with titles, company names, locations, descriptions, and apply links aggregated from multiple job boards.

google_lens

read

Analyze images using Google Lens. Upload an image URL to get visual matches, product identification, text extraction, and exact match detection. Supports refining results with a text query for search types: all and visual_matches. Required: url (a publicly accessible image URL).

google_local

read

Search local businesses, restaurants, and services via Google Search's local pack. Each result includes `place_id`, `data_id`, and `kgmid` in the same format as Google Maps. Chain handoffs: - `google_maps_place` / `google_maps_reviews` / `google_maps_photos` via `place_id` or `data_id` - `google_maps_directions` via `data_id` (place_id is not accepted by directions) - `google_place` via `kgmid` for the Knowledge Graph entity card For Maps-native search use `google_maps_search` instead.

google_maps_directions_search_along_route

read

Find places (gas stations, restaurants, hotels, etc.) along a Google Maps driving route. Two-step workflow: 1. Call the `google_maps_directions` tool with the origin and destination. 2. Pass the `search_along_route_token` from its response here, with `q` — the category of place to find (e.g., 'Gas', 'Restaurants').

google_maps_directions

read

Get directions between two locations on Google Maps for driving, walking, cycling, or flying (use `google_maps_directions_transit` for public-transit routing). Returns route options with distance, duration, turn-by-turn instructions, and a summary of all available travel modes. Both `from` and `to` are required. `from` and `to` accept addresses, place names, lat/lng coordinates (e.g., '40.758,-73.985'), or `data_id` from `google_maps_search`, `google_maps_place`, or `google_local` results (e.g., '0x89c25855c6480299:0x55194ec5a1ae072e'). Note: `place_id` (ChIJ...) is NOT accepted — use `data_id` when chaining from search results. The response includes a `search_along_route_token` — pass it to the `google_maps_directions_search_along_route` tool to find places (gas, restaurants, etc.) along this route.

google_maps_directions_transit

read

Get public-transit directions (bus, subway, train, tram/light rail) between two locations on Google Maps. Returns route options with distance, duration, transfer details, and turn-by-turn instructions. For driving, walking, cycling, or flying, use `google_maps_directions` instead. `from` and `to` accept addresses, place names, lat/lng coordinates (e.g., '40.758,-73.985'), or `data_id` from `google_maps_search`, `google_maps_place`, or `google_local` results (e.g., '0x89c25855c6480299:0x55194ec5a1ae072e'). Note: `place_id` (ChIJ...) is NOT accepted — use `data_id` when chaining from search results.

google_maps_photos

read

Get photos for a specific place on Google Maps. Requires `data_id` or `place_id` from `google_maps_search`, `google_maps_place`, or `google_local` results — at least one must be provided. Returns photo URLs with thumbnails.

google_maps_place

read

Get detailed information about a specific place from Google Maps. Requires a data_id or place_id obtained from google_maps_search results. At least one of data_id or place_id must be provided. Returns comprehensive place details including address, phone, hours, reviews, photos, and popular times.

google_maps_reviews

read

Get reviews for a specific place on Google Maps. Requires `data_id` or `place_id` from `google_maps_search`, `google_maps_place`, or `google_local` results — at least one must be provided. Returns reviews with user info, rating, text, date, and owner response.

google_maps_search

read

Search for local businesses and places on Google Maps. Returns local results with names, addresses, ratings, reviews, and contact information. Use the data_id or place_id from results with google_maps_place to get detailed place information.

google_news_light

read

Search Google News for recent articles and headlines. Returns news results with title, source, date, snippet, and thumbnail. Supports time filtering and relevance/recency sorting. Requires a search query in `q`. For general web search, use google_search_light instead.

google_patents_search

read

Search Google Patents for patent documents and scholarly articles. Returns patent titles, IDs, inventors, assignees, filing dates, and abstracts.

google_place

read

Google Knowledge Graph entity card for a place, organization, or thing. Distinct from `google_maps_place` — uses `kgmid` (e.g., '/m/02j81' or '/g/11b_3cn7rv') rather than a Maps `place_id` / `data_id`. Get a `kgmid` from `google_local` results (each result includes `place_id`, `data_id`, AND `kgmid`) or from `google_search` knowledge_graph results.

google_play_details

read

Get detailed information for an Android app on the Google Play Store. Returns app name, description, ratings, reviews, screenshots, version history, and developer info. Requires a product_id from google_play_search results (e.g., 'com.spotify.music'). When looking up games, use store 'apps' (not 'games').

google_play_search

read

Search for Android apps on the Google Play Store. Returns app listings with titles, ratings, prices, and developer info. Use google_play_details with a product_id from results to get full app details.

google_product

read

Get detailed product information from Google Shopping. Requires a product_token obtained from google_shopping_search results. Returns comprehensive product details including offers from multiple sellers, specifications, reviews, and pricing history.

google_rank_tracking

read

Get Google organic search results for SEO rank tracking. Returns up to 100 results per request with position, title, URL, and snippet. Ideal for monitoring keyword rankings and SERP analysis.

google_reverse_image

read

Search Google with an image instead of a text query. Returns the web results Google shows for the image (pages about what it depicts), visual matches (visually similar images with the pages that host them, plus price and stock on product matches), and related searches. Required: url (a publicly accessible image URL). For exact copies of the image or a text query alongside the image, use google_lens instead.

google_scholar_case_law

read

Get the full opinion and citation graph of a US federal or state court case on Google Scholar. Required: caselaw_id as a string of digits. To search by legal issue, party name, or citation, first call google_scholar_cases with q. Copy a result's exact caselaw_id into this tool. You can also use referenced_cases.caselaw_id from a previous opinion to follow citations. Returns the case header, reporter citations, dates, docket numbers, referenced cases, footnotes, and full opinion text.

google_scholar_cases

read

Search US federal and state court opinions (case law) on Google Scholar. Returns matching cases, each with a `caselaw_id`, the case `title`, and a `publication` string containing the court and reporter citation. Required: q (search query), e.g. {"q":"qualified immunity"}. Pass a result's `caselaw_id` to google_scholar_case_law to fetch the full opinion text and citation graph. Use google_scholar_courts to look up `court` values for specific district, bankruptcy, or state courts. For academic papers and articles (not case law), use google_scholar instead.

google_scholar_courts

read

Look up Google Scholar case-law `court` identifiers to use with google_scholar_cases. Search by keyword (state, circuit, district, "supreme court", "bankruptcy") and get back the `court` value to pass to google_scholar_cases. Example: query "louisiana" returns identifiers such as fifth_circuit_ed_louisiana and louisiana_supreme_court. Omit the query to list the common top-level courts.

google_scholar

read

Search Google Scholar for academic papers, citations, and scholarly articles. Returns results with titles, authors, publication info, citation counts, and links to PDFs. Use cites parameter to find papers citing a specific work, or cluster to find all versions of a paper. For US court opinions and case law, use google_scholar_cases instead.

google_search_light

read

Perform fast Google web searches. Returns organic search results, related searches, and pagination. Suitable for quick information retrieval when advanced filtering is not needed. Requires a search query in `q`.

google_shopping_search

read

Search for products on Google Shopping. Returns product listings with prices, sellers, ratings, and comparison shopping data. Use google_product tool with product_token to get detailed product information.

google_travel_explore_destination

read

Drill into a specific destination from `google_travel_explore` results — returns detailed flight options for that destination. Get `arrival_id` from `google_travel_explore` destinations (the `kgmid` field) or pass a 3-letter IATA airport code directly. Bounding-box coordinates are not supported by this tool — use `google_travel_explore` for area-based searches.

google_travel_explore

read

Discover flight destinations from a departure point — use when the user has a departure but no specific destination. Returns destinations with `name`, `kgmid`, `country`, and price/duration info. **Chain handoffs:** - To drill into a destination, pass its `kgmid` as `arrival_id` to `google_travel_explore_destination`. - For specific flight searches, use the destination `kgmid` with `google_flights_*` tools. - For hotels at the destination, pass the destination `name` (NOT kgmid) as the `q` parameter to `google_hotels` — Google Hotels does not accept kgmid.

google_vacation_rentals

read

Search for vacation rentals using Google Hotels. Provides pricing, ratings, amenities, and availability for vacation rental properties like apartments, villas, cabins, and houses worldwide.

instagram_comments

read

Fetch the comments on a public Instagram post. The first page also returns the post itself (caption, type, likes, author, full-size media links, carousel items, tagged users and the total comment count), then each comment's text, timestamp, like count and author profile, plus a pagination token for the next page. Photo posts, carousels, videos and reels all use the same shortcode. For the second and later pages, pass the next_page_token from the previous response; those pages return comments only, with no post block.

instagram_post

read

Fetch a public Instagram photo, video, reel, or carousel from its shortcode. Returns the caption, author profile with avatar, like and comment counts, timestamp, direct media URLs with dimensions and video duration, preview comments with their text and authors (has_more_comments signals more exist), tagged users, coauthors, location, topics, and carousel items with per-slide media. Required: post_id, the shortcode (DavpizrjugI in https://www.instagram.com/p/DavpizrjugI/) or the full post URL. Not the numeric media_id. Use instagram_profile with a username to list an account's recent posts and their shortcodes.

instagram_profile

read

Fetch public profile information from Instagram. Returns bio, follower/following counts, post count, list of posts, verification status, business category, and profile links. Each listed post's id is its shortcode; pass it to instagram_post for the full post, reel, or carousel details.

linkedin_ads_search

read

Search for ads in LinkedIn's Ad Library. Returns sponsored content, ads, and campaigns. At least one parameter is required. You can combine: q (keyword), advertiser (company name), country, or time_period.

meta_ads_page_search

read

Search for advertiser pages and locations in Meta's Ad Library (Facebook, Instagram). Returns page IDs, location IDs, and keyword suggestions matching your query. Use the returned page_id with meta_ads_search to find all ads from a specific advertiser.

meta_ads_search

read

Search for ads in Meta's Ad Library (Facebook, Instagram). Returns ad creatives, page info, and engagement data. At least one of `q` or `page_id` is required. To find a page_id, use meta_ads_page_search first. Then pass it here to see all ads from that advertiser.

perplexity

read

Get Perplexity's AI-generated answer to a question. Returns AI-synthesized text with cited source reference links.

tiktok_ads_search

read

Search for ads in TikTok's Ad Library. Returns video, image and carousel ads with advertiser info and estimated audience. `format` is `video` or `image`; carousels are `image` ads with several `image_urls`. You must provide either `q` (keyword), `advertiser_token` (preferred for filtering by advertiser), or `advertiser_id` to get results. Use `tiktok_advertiser_search` to find advertiser tokens.

tiktok_advertiser_search

read

Search for advertisers by name in TikTok's Ad Library. Returns advertiser suggestions and keyword matches. Use with tiktok_ads_search to find ads from a specific advertiser by passing the returned advertiser_id.

tiktok_autocomplete

read

Autocomplete a TikTok search query. Returns the suggestions TikTok's search box shows for a typed prefix as `suggestions`, in TikTok's ranking order, each with its `position`, `type` (`query` or `profile`), `value`, `language` code and predicted click-through rate `score` (0 to 1) when TikTok provides one. A `profile` suggestion is a TikTok account and also carries `username`, `name`, `link` and `is_verified`. Suggestions follow the query's own language, so a Japanese prefix returns Japanese suggestions. Set `country` for another market's suggestions, and `language` to rank them for a user with TikTok in that language (e.g. `country` 'BR' with `language` 'pt' for what local users see). Required: `q`. Use it to expand a seed keyword into the related phrasings people search on TikTok, then pass a chosen `value` as `q` to `tiktok_search` to fetch the matching videos, photos and profiles. An empty list means TikTok has no suggestions for that prefix. It is a valid answer, not an error.

tiktok_profile

read

Fetch public profile information from TikTok. Returns bio, follower/following counts, total likes (hearts), video count, verification status, and bio links.

tiktok_profile_videos

read

Fetch a public TikTok creator's video feed (their posts), paginated. Returns each video's caption, publish time, duration, dimensions, thumbnails, view/like/comment/share/save counts, sponsored flag, the sound it uses (with cover, duration, and originality flags), and the hashtags and mentions from the caption. Sort the feed with sort_by (latest, popular, or oldest) and page through it with next_page_token.

tiktok_search

read

Search TikTok by keyword and get the matching profiles, videos, and photos. Each video and photo returns its caption, publish time, engagement counts (views, likes, comments, shares, saves), thumbnails, the sound it uses, the hashtags and mentions from the caption, and the authoring creator. Profiles return the username, name, bio, avatar, verification, follower count, and total hearts. Scope the results with filter_by (all, videos, photos, or profiles) and page through them with next_page_token.

tiktok_transcript

read

Extract the transcript (captions) from a single TikTok video. Identify the video by url, or by video_id together with username; exactly one of these two forms is required. By default returns combined plain text (best for reading and summarization). Set output_format to 'json' for timestamped segments. Supports selecting a caption language.

tiktok_video

read

Fetch structured data for a single public TikTok video (or photo carousel). Identify the post by url, or by video_id together with username; exactly one of these two forms is required. Returns the video's caption, publish time, duration, thumbnail, play/like/comment/share/save counts, the sound it uses, and the hashtags and mentions from the caption, along with the author (username, display name, bio, avatar, verified/private flags, and follower/following/heart/post counts). Photo carousels also return the post title and each slide's image URL and dimensions.

tripadvisor_forums_search

read

Search TripAdvisor forum threads (community Q&A and discussions). Returns `forum_results` with thread `forum_id`, title, and link. For places (hotels, restaurants, attractions, destinations, airlines), use `tripadvisor` instead.

tripadvisor_place

read

Detailed information about a specific TripAdvisor place (hotel, restaurant, attraction, attraction product, destination, or airline). Returns description, ratings, photos, address, amenities, booking options where applicable, and a sample of reviews. **Note:** Requires a TripAdvisor numeric `place_id` from `tripadvisor` results. This is NOT a Google Maps `place_id`.

tripadvisor_reviews

read

Reviews for a specific TripAdvisor place (hotel, restaurant, attraction, attraction product, geo). Returns review text, rating, date, user info, and photos. Supports filtering by text, rating, trip type, time of year, and language. **Note:** Requires a TripAdvisor numeric `place_id` from `tripadvisor` results. NOT a Google Maps `place_id`.

tripadvisor

read

Search TripAdvisor for places — hotels, restaurants, attractions, destinations, and airlines. Returns results with a TripAdvisor `place_id` (numeric). For TripAdvisor forum threads, use `tripadvisor_forums_search` instead. **Note:** TripAdvisor's `place_id` is a numeric string — it is DISTINCT from Google Maps' `place_id` (ChIJ...) and the two are not interchangeable. Use TripAdvisor `place_id` ONLY with `tripadvisor_place` and `tripadvisor_reviews`.

walmart_product

read

Get detailed product information from Walmart. Requires a product_id obtained from walmart_search results. Returns comprehensive product details including pricing, specifications, reviews summary, and availability.

walmart_reviews

read

Get customer reviews for a Walmart product. Returns individual reviews (rating, text, author, date) plus an overall rating summary. Optionally filter by star rating or verified purchases, and sort the results. Required: product_id (from walmart_search or walmart_product results).

walmart_search

read

Search for products on Walmart. Returns product listings with prices, ratings, and availability. Use the walmart_product tool with the product_id or id field from results to get full details.

walmart_stores

read

Find Walmart store IDs near a US location. Provide a 5-digit ZIP code (most precise) or a city/state in "City, ST" format. Returns nearby Walmart stores with their store_id, postal_code, and address. Use the returned store_id as the store_id parameter of walmart_search or walmart_product to get store-specific pricing and availability. Required: location.

youtube_channel_posts

read

List the community posts of a YouTube channel from its Posts tab, about 10 per page. Posts can include text, likes, comments, poll or quiz results, attachments, and the original post for reposts. Responses include pagination.next_page_token for older posts, to be sent with the same channel_id. Required: channel_id (a channel ID like 'UCX6OQ3DkcsbYNE6H8uQQuVA' or an '@' handle like '@MrBeast'). For a single post, pass its link as url, or its id as post_id, to youtube_post. For details of a video attachment, use youtube_video.

youtube_hashtag

read

Get the videos or shorts YouTube lists under a hashtag. Returns the hashtag with its approximate video and channel counts, and up to 36 videos (title, channel, views, length, publish time, live and short flags) or shorts (title, views, thumbnail) per page. Required: hashtag (with or without the leading '#', only letters, numbers and underscores). Set search_type to 'shorts' for the shorts feed. To get the next page, call again with the same hashtag and search_type plus pagination.next_page_token from the previous response. Hashtags from youtube_post can be passed as they are. For video details, use youtube_video. To find videos by keyword instead of hashtag, use youtube_search.

youtube_post

read

Get a single YouTube community post from its URL or post ID. Returns the post text with resolved links and hashtags, exact like count, channel details, poll results (choices and total votes), quiz results (choices with the correct answer flagged and explanations), and image, video, or playlist attachments. Required: url (the community post URL) or post_id (the post ID, e.g. from youtube_channel_posts). Do not pass both. For video details, use youtube_video. To find videos by topic, use youtube_search.

youtube_search

read

Search YouTube for videos. Returns video results with titles, channels, view counts, and thumbnails. Use this to find videos on any topic. Requires a search query in `q`.

youtube_transcript

read

Extract transcripts from YouTube videos. By default returns combined plain text (best for reading and summarization). Set output_format to 'json' for timestamped segments. Supports multiple languages.

youtube_video

read

Get detailed information about a YouTube video. Returns video metadata including title, description, channel info, view count, comments, and related videos.

zillow_property

read

Get detailed information about a specific Zillow property or building. Returns address, pricing, Zestimate, photos, facts and features, schools, walk/transit/bike scores, comparables, price/tax history, and nearby listings. Pair with zillow_search to discover property IDs first, then call this tool to fetch full details. Provide either a numeric Zillow property ID (zpid) or a full Zillow URL (`https://www.zillow.com/homedetails/...` for properties or `https://www.zillow.com/apartments/...` for buildings).

zillow_search

read

Search for real estate listings on Zillow. Returns properties for sale, for rent, or recently sold with pricing, property details, and photos. Supports filtering by price, bedrooms, bathrooms, square footage, lot size, year built, home type, and listing status.

Connect SearchApi MCP to your agent

One endpoint, the same key, whichever client you use.

Apps

SDKs

Claude Desktop

Claude Desktop

~/Library/Application Support/Claude/claude_desktop_config.json (Mac) · %APPDATA%\Claude\claude_desktop_config.json (Windows)

JSON
{
  "mcpServers": {
    "mewcp": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://gateway.mewcp.com/personal/mcp",
        "--header",
        "Authorization:${AUTH_HEADER}"
      ],
      "env": {
        "AUTH_HEADER": "Bearer API_KEY"
      }
    }
  }
}

Replace API_KEY with your own key.

Already have an "mcpServers" section in your config? Just add the server entry inside it.

  1. 01Open Claude Desktop → Settings → Developer → "Edit Config"
  2. 02Paste the snippet inside the outer { } of the config file (merge with your existing "mcpServers" section if you have one)
  3. 03Save the file, then quit Claude Desktop completely and reopen it
  4. 04Start a new conversation — your tool will be available

One endpoint. Every service.

VS CodeAny agent
One Gateway

Firecrawl

API Key

Web Scrapper

No auth

Context.dev

API Key

SearchApi MCP

OAuth

Discovery, routing, credentials, tool scoping and execution logs all happen at the gateway→connections stay ACTIVE with no work from you

Separate connections░░░░░░░░░░░░░░░░░░░░░░░░░░░░140 tool definitions ~22k tokensWith MewCP░░░░░░░░░░░░░░░░░░░░░░░░░░░░4 meta-tools ~2.3k tokens

Built for AI agents

SearchApi MCP runs through a gateway that holds the credentials, scopes the access and records every call.

Managed authentication

  • OAuth to SearchApi MCP handled end to end, with tokens refreshed before they expire.
  • One credential per end user, not one shared key across your users.
  • Reconnect an account without touching your agent's config.

Credentials stay out of context

  • SearchApi MCP credentials are resolved at the gateway and attached to the outbound call.

Ready to connect SearchApi MCP?

Managed auth, hosted MCP servers, and every SearchApi MCP tool your agent needs.

Free to start.

  • The agent sees tool results, never a token.
  • Revoke an account and the next call stops working — no redeploy.
  • Scoped access, fully logged

    • Choose exactly which SearchApi MCP tools an agent is allowed to call.
    • Every call is logged with its outcome, latency and which account it ran as.
    • Catalog changes are reviewed before they ship, so tool descriptions cannot shift under you.

    One endpoint for every server

    • Reach SearchApi MCP through the same MCP endpoint as the rest of your toolset.
    • Tools are discovered on demand, so 107 tools do not fill the context window.
    • Stateless: no sessions to keep alive and no reconnect logic.