Google Flights Deals

io.github.johnisanerdv1.0.0更新於 Oct 6, 2026

Cheapest destinations from an airport, each with its fare and that route's typical price.

已驗證Streamable HTTP可網頁執行Web Search & ScrapingLocation & Lifestyle

概覽

AI 產生的概覽

找出從指定機場出發最便宜的目的地,並附上票價、該航線的典型價格與特價標記。

功能
輸入一個或多個出發機場後,回傳最多三十個最便宜的目的地,格式為結構化 JSON。每筆資料包含價格、該航線的典型價格、在本機計算的節省金額與節省百分比、is_below_typical 標記、日期、航空公司、轉機次數、時長與訂票連結。篩選條件包括艙等、最高價格、最多轉機次數、旅遊天數,以及航空公司的包含或排除。
適用情境
適合想知道從某個常用機場出發可以去哪些便宜目的地,或想把便宜票價清單篩選出真正划算的選項。它適合一次性的目的地研究,而不是長期的價格追蹤。
執行需求
透過 Apify MCP 伺服器存取 mcp.apify.com 上的遠端 MCP 端點。需要 Apify 帳號與 API 權杖,可透過瀏覽器 OAuth 或 Authorization Bearer 標頭提供。部分用戶端需要開啟開發人員模式或設定連接器。
安裝前請注意
Apify API 權杖屬於憑證,請勿寫入共用的設定檔。每次查詢都會消耗 Apify 用量,付費方案下可能產生費用。此伺服器只回傳一次快照,不追蹤價格變化、不保留歷史紀錄,也不會發送通知。設定 maxDurationMinutes 會關閉典型價格基準,連帶停用特價偵測。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Google Flights Deals,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable,透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "google-flights-deals": {
      "type": "http",
      "url": "https://mcp.apify.com/?tools=johnvc/google-flights-deals-api"
    }
  }
}

README

✈️ Google Flights Deals API: cheap destinations as clean JSON

Give it an airport and get back the thirty cheapest destinations you can fly to from there, as structured JSON. Each one comes with the price, the typical price for that route, exact dates, airline, stops, duration, a photo, and a booking link.

The part nobody else gives you: which of them are actually bargains. A cheap fare and a good deal are not the same thing.

Actor: Google Flights Deals API on Apify Store

Video Walkthrough

https://www.youtube.com/watch?v=jREWahDGhJM

Quick Start

bash
git clone https://github.com/johnisanerd/Apify-Google-Flights-Deals-API.gitcd Apify-Google-Flights-Deals-APIcp .env.example .env          # paste your Apify tokenuv syncuv run google-flights-deals-api-example.py

Get a free Apify API key at apify.com.

Why Use This Google Flights Deals API?

  • Bargain detection, not just cheap fares. Every row carries average_price, what that route typically costs, plus savings, savings_percent, and an is_below_typical flag.
  • One call, thirty bookable options. Each with real dates and a link that goes straight to the booking page.
  • A real filter surface. Cabin class, max price, max stops, trip length, airline include or exclude.
  • No arrival airport needed. This answers "where can I go cheaply from here", so the source ignores a destination by design.

An honest note on the data

Measured across three hubs, roughly 6 to 30% of the feed genuinely beats its typical price, depending on the airport. The rest are cheap in absolute terms without being discounts, usually short-haul routes. That is the nature of the source, and it is exactly why is_below_typical exists: it turns a list of cheap flights into a list you can filter for bargains.

One limit worth knowing: setting maxDurationMinutes makes the source stop returning the typical-price baseline, so that single filter turns off bargain detection. Every other filter keeps it, including one way.

Features

FeatureDetail
Bargain flagis_below_typical is true only when the fare beats its own route's typical price
Derived savingssavings and savings_percent, computed locally on every row
Multi-airportdepartureIds watches several home airports in one run
Filterscabin class, max price, max stops, trip length preset, airline include or exclude
Booking linksflight_link goes straight to the itinerary
Localizationcurrency, hl, and gl

Usage Examples

Nonstop options under a budget:

python
run_input = {"departureId": "LAX", "maxStops": "nonstop", "maxPrice": 400}

Weekend trips from a set of home airports:

python
run_input = {"departureIds": ["JFK", "EWR", "LGA"], "travelDuration": "weekend"}

Business class bargains:

python
run_input = {"departureId": "LAX", "travelClass": "business"}

Input Parameters

ParameterTypeDescription
departureIdstring3-letter IATA code, such as JFK.
departureIdsarrayMore airports. Each is one lookup.
tripTypeselectRound trip (default) or one way. Both keep the savings baseline.
outboundDate / returnDatestringYYYY-MM-DD. Leave blank to let the feed pick cheap dates.
travelDurationselectany, one_week, weekend, two_weeks
tripLengthstringExact days, as 7 or a range like 5-10.
travelClassselecteconomy, premium_economy, business, first
maxPriceintegerDrop deals above this price.
maxStopsselectany, nonstop, one_stop, two_stops
maxDurationMinutesintegerDrop longer deals. Turns off bargain detection, see above.
includeAirlines / excludeAirlinesstringComma-separated codes. Mutually exclusive.
maxDealsPerAirportintegerDefault and maximum 30.
currency, hl, glstringCurrency, language, country.

Output Format

One row per destination:

json
{  "result_type": "deal",  "position": 1,  "departure_id": "JFK",  "name": "Nantucket",  "country": "United States",  "price": 295,  "average_price": 478,  "savings": 183.0,  "savings_percent": 38.3,  "is_below_typical": true,  "route": "JFK to ACK",  "outbound_date": "2026-10-01",  "return_date": "2026-10-08",  "flight_duration": 282,  "stops": 1,  "airline": "JetBlue",  "flight_link": "https://www.google.com/travel/flights?tfs=..."}

Negative savings are preserved rather than hidden: knowing a "deal" sits above its typical price is useful information.

This Actor returns a snapshot. It does not track prices over time, keep history, or send alerts. It is the data layer you build a price-alert product on.

Install in Claude Cowork Desktop

[Install in Claude Cowork Desktop]

Cowork is the desktop app's automation mode. To give it the Google Flights Deals API as a tool, add the Apify MCP server as a connector.

  1. Open the Claude desktop app and go to Settings → Connectors (or Settings → Developer → Edit Config to edit claude_desktop_config.json directly).
    • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
    • Windows: %APPDATA%\Claude\claude_desktop_config.json
  2. Add the Apify MCP server, preloaded with only this Actor:
json
{  "mcpServers": {    "apify": {      "command": "npx",      "args": [        "-y",        "mcp-remote",        "https://mcp.apify.com/?tools=actors,docs,johnvc/google-flights-deals-api"      ]    }  }}
  1. Restart the app. When Cowork first calls the tool, complete the OAuth prompt in your browser, or add your Apify API token in the connector settings to skip OAuth.
  2. In a Cowork chat, confirm the tool is available and ask it to run the Google Flights Deals API.

Download the desktop app and start a free trial: https://claude.ai/referral/uIlpa7nPLg More help: https://docs.apify.com/platform/integrations/claude-desktop

Install in Claude Code

[Install in Claude Code]

Claude Code is the command-line tool. Add the Actor's MCP server with one command:

bash
claude mcp add --transport http apify \  "https://mcp.apify.com/?tools=actors,docs,johnvc/google-flights-deals-api"

To use a token instead of browser OAuth:

bash
claude mcp add --transport http apify \  "https://mcp.apify.com/?tools=actors,docs,johnvc/google-flights-deals-api" \  --header "Authorization: Bearer YOUR_APIFY_TOKEN"

Then verify with claude mcp list, or run /mcp inside a session. Ask Claude Code to call the Google Flights Deals API.

Try Claude Code free: https://claude.ai/referral/uIlpa7nPLg Claude Code MCP docs: https://code.claude.com/docs/en/mcp

Install in Claude (website)

[Install in Claude (website)]

On claude.ai you add Apify as a connector, then enable just this Actor's tool.

  1. Go to Settings → Connectors → Browse connectors and search for Apify MCP server. Install it (enable or update if prompted).
  2. When connecting, authenticate with your Apify API token, and enable the tool johnvc/google-flights-deals-api.
  3. In any chat, open + → Connectors and turn on Apify.
  4. Alternatively, choose Add custom connector and paste the full MCP URL https://mcp.apify.com/?tools=actors,docs,johnvc/google-flights-deals-api, using OAuth when prompted.
  5. Ask Claude to run the Google Flights Deals API.

Open Claude on the web: https://claude.ai/referral/uIlpa7nPLg

Install in Cursor

[Install in Cursor]

Cursor reads MCP servers from a project file at .cursor/mcp.json.

  1. In your project, create .cursor/mcp.json:
json
{  "mcpServers": {    "apify": {      "url": "https://mcp.apify.com/?tools=actors,docs,johnvc/google-flights-deals-api"    }  }}
  1. If you prefer token auth over browser OAuth, add a header:
json
{  "mcpServers": {    "apify": {      "url": "https://mcp.apify.com/?tools=actors,docs,johnvc/google-flights-deals-api",      "headers": { "Authorization": "Bearer YOUR_APIFY_TOKEN" }    }  }}
  1. Open Cursor → Settings → MCP and confirm the apify server is connected (green dot).
  2. In Composer or Chat, ask Cursor to call the Google Flights Deals API.

New to Cursor? Get it here: https://cursor.com/referral?code=XQP4VBLI3NNX

Install in ChatGPT

[Install in ChatGPT]

ChatGPT connects to the Apify MCP server through Developer mode (available on ChatGPT Pro, Plus, Business, Enterprise, and Education plans).

  1. Click your profile icon, then go to Settings > Apps. If you do not see a Create app button, open Advanced settings and enable Developer mode.
  2. Click Create app and fill out the form:
    • Name: Apify
    • MCP Server URL: https://mcp.apify.com/?tools=actors,docs,johnvc/google-flights-deals-api
    • Authentication: OAuth
  3. Click Create and authorize the connection with Apify.
  4. To use the app in a conversation, click + in the chat, choose Developer mode, and select Apify.

More help: https://docs.apify.com/platform/integrations/mcp


Made with care

Use the Google Flights Deals API to power local lead lists, market research, and place data for your product or AI agent.

Featured Tasks

Ready-to-run examples on the Apify Store, each targeting one local-data use case:

🤖 Ask an AI assistant about this Actor

Open a ready-to-send prompt about the Google Flights Deals API in the AI of your choice:

Last Updated: 2026.09.22

來源:README.md,提交 cd84639

工具

0
工具後設資料尚未被收錄。

版本歷史

1
  1. v1.0.0最新Sep 16, 2026