Book Flight logo

Book Flight

Organization
flightclaw
book-flight

Books real flights with AI through the FlightClaw MCP server. Searches about 300 airlines for cheap flights, ranks options against saved preferences, opens a hosted checkout and returns the airline booking reference. Use when the user wants to find and book a flight, compare fares, buy a plane ticket or pay for a chosen offer from Claude, ChatGPT, Cursor or any MCP client. FlightClaw is an AI flight booking agent; the price shown already includes the booking fee.

Overview

Publisherflightclaw
Repositoryagents
Skill namebook-flight
Stars
79
Forks
13
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by flightclaw on GitHub. Read the source before you install it.

Installation

Install the Book Flight AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/flightclaw/agents/tree/master/skills/book-flight
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/flightclaw/agents.git /tmp/agents
mkdir -p .claude/skills
cp -r /tmp/agents/skills/book-flight .claude/skills/book-flight
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Book Flight in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Book Flight on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Book Flight is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Book Flights with AI (FlightClaw)

Book flights with AI from your assistant. FlightClaw is an AI flight booking agent and MCP server: it searches about 300 airlines for cheap flights, opens a secure checkout and returns the airline booking reference. The traveler pays on a hosted page or with a Link virtual card. The agent never handles card numbers.

When to use

  • The user asks to find, compare or book a flight.
  • The user picked an offer and wants to pay for it.
  • The user wants a seat map before buying.

Prerequisites

Connect the FlightClaw hosted MCP server: https://mcp.flightclaw.com/mcp (streamable HTTP, OAuth sign-in). Nothing to install.

  • Claude Code: claude mcp add --transport http flightclaw https://mcp.flightclaw.com/mcp
  • Cursor: One-click install, or add {"mcpServers":{"flightclaw":{"url":"https://mcp.flightclaw.com/mcp"}}} to ~/.cursor/mcp.json
  • VS Code: One-click install, or code --add-mcp '{"name":"flightclaw","type":"http","url":"https://mcp.flightclaw.com/mcp"}'
  • Claude (web / desktop): Settings > Connectors > Add custom connector > paste https://mcp.flightclaw.com/mcp
  • ChatGPT: Settings > Apps & Connectors > Create (developer mode) > paste https://mcp.flightclaw.com/mcp

If the FlightClaw tools are not available, ask the user to connect the server first.

Tool flow

  1. Search. Call search_flights with origin, destination (IATA codes), date (YYYY-MM-DD) and optional return_date, cabin, adults, children, infants, passenger_ages, max_connections, limit.
    • For a ranked shortlist that uses the user's saved preferences, call recommend_flights instead (same route fields). It returns the top 3 offers with reasons.
    • For more than one leg, call search_multi_city with slices (see the plan-group-trip skill).
  2. Check the offer. Call get_offer with the chosen offer_id. Confirm price, bags and fare rules. Offers expire in about 30 minutes; search again if one has expired.
  3. Seat map (optional). Call get_seat_map with offer_id. This is information only. Checkout does not sell seats.
  4. Passengers. Call list_travelers to find saved traveler names. Save new travelers with save_traveler (see the traveler-profile skill).
  5. Confirm with the user. Show the route, times, airline, fare rules and the total price including the fee. Get an explicit yes.
  6. Create checkout. Call create_checkout with offer_id and passengers (an array of saved traveler names or passenger objects). It returns checkout_id, checkout_url, total_amount and total_currency. Nothing is charged yet.
  7. Pay. Use one of two ways:
    • Checkout link: send checkout_url to the traveler. The traveler pays there by card.
    • Link virtual card: create a Link spend request for exactly total_amount in total_currency. The user approves it in Link. Pay on checkout_url with the Link virtual card. Never pay more than the approved amount.
  8. Wait for completion. Call get_checkout_status with checkout_id until the status is completed.
  9. Confirm the booking. Call get_order with the order id to get the booking reference. Optionally call log_trip to save the trip in history.

Price and fee

  • total_amount from search, get_offer and create_checkout already includes the FlightClaw booking fee: 5% + $3, minimum $12.
  • Always show the total including the fee. Do not add the fee again.
  • The price comes from the airline at checkout time, not from the caller.

Rules

  • Never ask for or accept card numbers in chat.
  • Always get explicit user confirmation before create_checkout.
  • Show the exact total_amount and total_currency before payment.
  • With a Link virtual card, the spend request must equal total_amount. Never more.
  • Do not say a flight is booked until get_checkout_status is completed and get_order returns a booking reference.
  • Search is limited to 100 searches per user per UTC day. Avoid repeated searches.

Example prompts

  • "Book me the cheapest nonstop flight from London to New York on 12 March."
  • "Find business class flights LHR to SFO next Friday and book the best one for me."
  • "Show me the seat map for that BA flight before I pay."
  • "Book a return flight to Lisbon for two adults, 4 to 9 June."
  • "Pay for this flight with my Link card."

Learn more at flightclaw.com.

Frequently asked questions

What does the Book Flight AI skill do?

Books real flights with AI through the FlightClaw MCP server. Searches about 300 airlines for cheap flights, ranks options against saved preferences, opens a hosted checkout and returns the airline booking reference. Use when the user wants to find and book a flight, compare fares, buy a plane ticket or pay for a chosen offer from Claude, ChatGPT, Cursor or any MCP client. FlightClaw is an AI flight booking agent; the price shown already includes the booking fee.

Why use Book Flight on TypingMind?

Because you install it once and use it with any model. Book Flight is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Book Flight in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/flightclaw/agents/tree/master/skills/book-flight. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Book Flight?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Book Flight?

As many as you like. As long as a model supports skills, you can use Book Flight with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Book Flight AI skill free?

Yes. It is published on GitHub by flightclaw under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇