punitarani/fli

Google Flights MCP, CLI and Python Library

What it solves

Fli provides a way to programmatically search for flights and find the cheapest travel dates using Google Flights data. It avoids the fragility of web scraping by interacting directly with Google Flights' internal APIs through reverse engineering, making the search process faster and more reliable.

How it works

Instead of parsing HTML or using browser automation, Fli issues specific GET requests to Google's public search page using protobufs. It then extracts the flight data from the inline AF_initDataCallback blob within the page's response. This approach allows it to support a wide range of filters (cabin class, stops, airlines, and alliances) and handle complex search queries, including round-trips and flexible date ranges.

Who it’s for

Developers who need to integrate flight search functionality into their applications, or power users who prefer a CLI interface for finding flight deals and filtering results.

Highlights

  • Direct API Interaction: Uses reverse-engineered APIs rather than web scraping for improved speed and reliability.
  • MCP Server: Includes a Model Context Protocol (MCP) server that allows AI agents (like Claude Desktop) to search for flights and find cheapest dates.
  • Comprehensive Filtering: Supports detailed filters for cabin class, airline alliances, layover durations, and specific departure windows.
  • Flexible Search: Supports one-way, round-trip, and multi-city searches (though multi-city is handled by searching each leg separately).
  • Built-in Protections: Includes rate limiting, automatic retries, and error handling to maintain stability.

Related

  • Project
    tmc/nlm

    A single-binary CLI client and MCP server for NotebookLM that enables terminal-based interaction, automation, and AI agent integration via a reverse-engineered wire protocol.

  • Project
    alibaba-flyai/flyai-skill

    A travel search skill for AI agents that connects them to Fliggy's real-time inventory for flights, hotels, and attractions via a CLI.

  • Project
    LetsFG/LetsFG

    LetsFG is an AI-integrated travel search and booking engine that provides real-time, transparent pricing for flights and hotels, allowing AI agents to perform bookings directly without the price inflation of traditional travel sites.

  • Project
    makeplane/plane-mcp-server

    Plane MCP Server is a Python service that exposes Plane’s project‑management API as Model Context Protocol tools, letting LLM agents read and modify Plane resources via stdio or HTTP (OAuth or API‑key). It offers 30 resource‑specific tools, PQL querying, and backward‑compatible naming, all under an MIT license.

  • Project
    dmtrKovalenko/fff

    fff is a Rust‑based, in‑memory file‑search library with fuzzy, frecency‑aware indexing. It powers a Neovim plugin, an MCP server for AI agents, and a Pi extension, offering ultra‑fast path and content searches that are cheaper for LLMs than traditional greps.