Google Flights

Name: Google Flights
Author: andreacappelletti97

by andreacappelletti97version 1.0.3i★ –iRuns on your computer

Registry nameio.github.andreacappelletti97/google-flights

Install

Overview

Description from the maker (original English)

MCP server for Google Flights: search, price tracking, cabin comparison, emissions, and more.

PopNx MCP’s three pillars

These three are never merged into one score: opinions, measurements and popularity are different things.

User voiceiNo reviews yetReviews open together with accounts in a later step
Our basic checksi1 of 1 passedChecked from public information; code not scanned yet
UsageiNot measured yet★ –

What you can do with it

We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.

Connection: Runs on your computer
Transport: stdio
Category: Search & AI memory

Install

Pick the AI app you use, then copy the settings.

Before you install

Basic checks: 1 of 1 passed
Runs on your computer with your user’s permissions (files, network, apps).
The registry lists no key to fill in.

You need

npmNode.js installed (for the npx command)

Which app do you use?

ClaudeClaude CodeCursorVS CodeChatGPT

Pick your app above. We remember it, so next time the button says “Install in …”.

Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json

{
  "mcpServers": {
    "google-flights": {
      "command": "npx",
      "args": [
        "-y",
        "google-flights-mcp"
      ]
    }
  }
}

Run this in your terminal

claude mcp add google-flights -- npx -y google-flights-mcp

Open in Cursor

Or copy the settings yourself

Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "google-flights": {
      "command": "npx",
      "args": [
        "-y",
        "google-flights-mcp"
      ]
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

Open in VS Code

Or copy the settings yourself

Paste into .vscode/mcp.json in your project

{
  "servers": {
    "google-flights": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "google-flights-mcp"
      ]
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.

Your choice stays on this device in a cookie; no account needed.

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

What it can do

Runs on your computer; the tool list appears in your AI app after you install it.

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026

✓ Pass
Maker matches the repo
The registry name was verified with the GitHub account andreacappelletti97, which owns the repo
… Not checked yet
Still maintained
We have not read this repo from GitHub yet
… Not checked yet
Has a licence
We have not read this repo from GitHub yet
– Not applicable
Endpoint responds
This one runs on your computer; there is no internet endpoint
– Not applicable
Sign-in with OAuth
Runs on your computer and uses local settings instead
… Not checked yet
No hidden instructions in tool descriptions
Runs on your computer; we can only read tool lists from internet endpoints

Compared with others in Search & AI memoryi

More stars than 0% of the other 7251 servers in this category
Published to the registry more recently than 9% of the other 7251 servers in this category
Basic checks equal to or better than 100% of the other 7251 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is Google Flights safe?

It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

The registry does not list a required key, though some servers ask you to sign in on first use.

Does it run on my computer or in the cloud?

It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).

Is it still maintained?

The GitHub repo last changed –, and the latest version (1.0.3) reached the registry 7 months ago.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.

What can I use instead?

In the same category: Context7, Codebase Memory, Exa

Alternatives

Servers in the same category from other makers, sorted by stars.

Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

Context7

by upstash

Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.

Computer or cloud★ 64,224MITUpdated today

Install

Codebase Memory

by DeusData

Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.

Runs on your computer★ 48,148MITUpdated 20 days ago

Install

Exa

by exa-labs

Connect AI agents to Exa for web search, content fetching, and multi-step research.

Runs in the cloud★ 5,213MITUpdated last month

Install

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

google-flights-mcp

The most feature-rich MCP server for Google Flights. No API key required.

12 tools for searching flights, tracking prices, comparing cabins, analyzing layovers, and more, all powered by real-time Google Flights data.

Works with Claude Desktop, Claude Code, Cursor, and any MCP-compatible client.

Features no other Google Flights MCP has

Carbon emissions per flight and per leg (CO2 in kg)
Price context: Google's own assessment of whether a price is low, typical, or high
Price tracking: track prices over time with SQLite persistence, detect drops and trends
Calendar heatmap: the cheapest fare for each day of a window of up to 31 days
Cabin class comparison: economy vs premium vs business vs first, side by side
Nearby airport suggestions: find cheaper alternatives (e.g., EWR/LGA near JFK)
Layover analysis: connection time risk assessment (tight/comfortable/overnight)
Aircraft & seat details: Boeing 787 vs 777, seat pitch in inches
Google Flights URLs: direct booking links users can click

What you can ask

*"Find nonstop flights from JFK to London next month"*
*"What's the cheapest week to fly SFO to Tokyo?"*
*"Compare economy vs business class for LAX to Paris"*
*"Are there cheaper airports near JFK I should check?"*
*"Track the price of SFO to NRT on June 15 and alert me if it drops"*
*"Show me the emissions for flights from SFO to Tokyo"*
*"Analyze the layovers for connecting flights from SFO to Bangkok"*

Quick start

Option 1: npx (no install)

Works immediately with Claude Code:

claude mcp add google-flights -- npx -y google-flights-mcp

Or with Claude Desktop, add to your claude_desktop_config.json:

"mcpServers": { "google-flights": { "command": "npx", "args": ["-y", "google-flights-mcp"] } } }

Option 2: Install from source

git clone https://github.com/andreacappelletti97/google-flights-mcp.git

cd google-flights-mcp npm install npm run build

Then connect to Claude Code:

claude mcp add google-flights node /absolute/path/to/google-flights-mcp/dist/index.js

Or Claude Desktop (claude_desktop_config.json):

"mcpServers": { "google-flights": { "command": "node", "args": ["/absolute/path/to/google-flights-mcp/dist/index.js"] } } }

Restart your MCP client. You should see 12 flight tools available.

Tools (12)

Search

Tool	Description
`search_flights`	One-way & round-trip search. Returns prices, airlines, durations, stops, aircraft, seat pitch, CO2 emissions, and price context.
`search_multi_city`	Multi-leg itinerary search (2-5 segments). Currently unavailable: Google serves multi-city results only to its own signed page requests (see Limitations). Search each leg with `search_flights`.

Price intelligence

Tool	Description
`get_calendar_heatmap`	Cheapest one-way fare for each day from `departureDate` (14 days by default, up to 31). Cheapest dates at a glance.
`get_price_insights`	Rank the departure dates in a range (up to 31 days) from cheapest to most expensive.
`compare_cabin_classes`	Compare economy, premium economy, business, and first class prices for the same route.
`track_price`	Record current price and report trend (dropping/rising/stable). Persists in SQLite.
`get_price_history`	View all recorded price observations for a tracked route.
`list_tracked_routes`	List all routes being price-tracked with last known price.

Airport tools

Tool	Description
`lookup_airport`	Search 8,800+ airports by city, name, IATA code, or country.
`find_nearby_airports`	Find alternative airports within a radius (default: 200km). Uses Haversine distance.

Utility

Tool	Description
`get_flight_url`	Generate a direct Google Flights booking URL.
`analyze_layovers`	Analyze connection quality for multi-stop flights. Reports risk level, connection type, aircraft.

Example output

search_flights (with emissions and price context)

Flights from SFO to NRT on 2026-06-15:

Price assessment: HIGH ($294 above typical). Range: $500 - $700, typical: $577

Flight 1: $874 | 11h 15m | 0 stop(s) | CO2: 428kg ZG 25: SFO -> NRT (11h 15m) [aircraft: Boeing 787, seat pitch: 31 inches, CO2: 428kg]

Flight 2: $1310 | 11h 5m | 0 stop(s) | CO2: 545kg NH 7: SFO -> NRT (11h 5m) [aircraft: Boeing 777, seat pitch: 34 inches, CO2: 545kg]

get_calendar_heatmap

Price calendar (one-way, cheapest per day): SFO -> NRT

14 days of data

Cheapest: $384 (2026-02-12) Most expensive: $870 (2026-04-13) Average: $632

2026-02: 12: $384 * 13: $384 * ... 20: $540 *** 2026-03: 06: $609 * ... 20: $689

find_nearby_airports

Airports near JFK within 150km:

LGA - LaGuardia Airport (New York, US), 17km away EWR - Newark Liberty International Airport (Newark, US), 33km away HPN - Westchester County Airport (White Plains, US), 48km away

How it works

There is no official Google Flights API. This server loads Google Flights' public search page and reads the result data the page embeds, the same data Google's internal FlightsFrontendService returns. It extracts not just flights, but hidden metadata: emissions, price assessments, daily price calendars, aircraft types, and seat details.

Reliability

Caching: 5-minute TTL cache, identical searches don't hit Google twice
Retry with backoff: exponential backoff + jitter on 429/5xx errors, honors Retry-After headers
Circuit breaker: stops requests after 5 consecutive failures, auto-recovers after 30s
Structural validation: clear errors when Google changes their response format
Paced fan-out: round trips and calendars load several pages; they go out a few at a time (GF_MCP_MULTILEG_CONCURRENCY, GF_MCP_CALENDAR_CONCURRENCY)
TLS mitigation: undici with browser-like headers + rotating User-Agents, fetch fallback

Price tracking

Price history is stored in SQLite at ~/.google-flights-mcp/prices.db. Each call to track_price records the current cheapest price and reports the trend compared to previous observations.

Development

npm install         # Install dependencies

npm run build # Build with tsup npm test # Run tests npm run lint # ESLint with FP rules (no-let, immutable-data, no-loop-statements) npm run typecheck # TypeScript strict type checking npm run check # typecheck + lint + test (the full CI pipeline) npm run dev # Build in watch mode

Design

Fully functional TypeScript codebase:

No mutation: all types readonly, no let/var/.push()/for loops
Result monad: errors are values (Result ), not exceptions
Pure/IO separation: pure transforms are separate from network and disk IO
Composition: pipe() + flatMap() for chaining fallible operations

See CLAUDE.md for architecture details and the Google Flights response format reference.

Limitations

No official API: reads data embedded in Google's public search page, which can change at any time. Structural validation makes breakages obvious.
Multi-city is unavailable: since August 2026 Google's internal flight endpoints only accept requests signed by its own page JavaScript, and the public page carries no rows for multi-city trips.
Calendars cost one page per day: Google's single-call calendar endpoint is gated the same way, so get_calendar_heatmap and get_price_insights search each day, up to 31 days.
Not encoded: maxPrice and maxDuration are applied to the results after the search, so a capped search can return fewer options.
Rate limiting: Google may throttle heavy use. Built-in retry and circuit breaker handle transient issues.
Prices are estimates: prices reflect query time; they can change before booking.
Currency: determined by Google based on IP/locale.

Contributing

Fork the repo
Create a feature branch
Make your changes
Run npm run check to verify
Open a PR

License

ISC

Google Flights

Overview

PopNx MCP’s three pillars

What you can do with it

Install

Before you install

What it can do

Basic checksi

Maker matches the repo

Still maintained

Has a licence

Endpoint responds

Sign-in with OAuth

No hidden instructions in tool descriptions

Compared with others in Search & AI memoryi

Common questions

Alternatives

Context7

Codebase Memory

Exa

README from the maker

google-flights-mcp

Features no other Google Flights MCP has

What you can ask

Quick start

Option 1: npx (no install)

Option 2: Install from source

Tools (12)

Search

Price intelligence

Airport tools

Utility

Example output

search_flights (with emissions and price context)

get_calendar_heatmap

find_nearby_airports

How it works

Reliability

Price tracking

Development

Design

Limitations

Contributing

License