Travala Travel MCP

Travala Travel MCP

Travala Travel MCP is the first end-to-end agentic AI travel protocol. It lets AI/ MCP clients search live hotel inventory on 2.2M+ properties, compare room packages and complete bookings, with payment settled on-chain in USDC on the Base network via x402 protocol. OAuth-secured; booking & cancellation are identity- & OTP-protected. Developers earn rewards on bookings driven through their agents.

Category
Visit Server

README

Travala MCP

MCP server for hotel search and booking via Travala.com. Enables AI agents to search hotels, compare room packages, and complete bookings — including payment — through natural language.

Tools

travala_search_hotel

Search for hotels by location and dates.

Inputs:

Parameter Type Required Description
location string City, region, or hotel name (e.g. "Paris", "Bali")
checkIn string Check-in date in YYYY-MM-DD format
checkOut string Check-out date in YYYY-MM-DD format
rooms string[] Room occupancy strings (e.g. ["2"] = 1 room, 2 adults)
lat / lng number Coordinates for more precise results
minPrice / maxPrice number Price range per night in USD
filters string[] all_inclusive, free_breakfast, swimming_pool, ocean_view
response_format string markdown (default) or json

Returns: List of hotels with name, star rating, price, amenities, and a sessionId for subsequent calls.


travala_search_package

Get available room types and rate plans for a specific hotel.

Inputs:

Parameter Type Required Description
hotelId string Hotel ID from travala_search_hotel result
sessionId string Session ID from the same search flow
checkIn / checkOut string Dates (if not carried from session)
rooms string[] Room occupancy (if not carried from session)
filters string[] Same filter options as hotel search
response_format string markdown (default) or json

Returns: Room types, rate plans, meal inclusions, refund policies, and a packageId for booking.


travala_book

Book a hotel package and initiate payment.

Inputs:

Parameter Type Required Description
packageId string Package ID from travala_search_package
sessionId string Session ID from travala_search_hotel
customer.firstName string Guest first name
customer.lastName string Guest last name
customer.email string Guest email
customer.phone string Guest phone with country code (e.g. +1...)

Returns: Booking confirmation with booking ID and payment instructions (x402 payment protocol).


travala_book_status

Recovery lookup for a travala_book call that errored, timed out, or returned a missing/garbled response. Use this before retrying — the booking may have already succeeded server-side, and a blind retry would double-charge the user.

Inputs:

Parameter Type Required Description
packageId string Same packageId sent to the failed travala_book
sessionId string Same sessionId sent to the failed travala_book

Returns: An interpretation field and httpStatus that tell the agent how to proceed:

interpretation httpStatus Meaning
completed 200 Booking succeeded. body contains the confirmation — present as success, do NOT retry payment.
in_progress 202 Server still settling. Wait body.retry_after_ms, then poll again (cap ~6 polls).
not_found 404 Nothing happened server-side. Safe to retry travala_book.
invalid_request 400 Check packageId/sessionId; session may have expired.
server_error 5xx Recovery endpoint down. Tell user to check email for confirmation; do not retry.

travala_manage_bookings

Look up details of an existing booking.

Inputs:

Parameter Type Required Description
bookingId string Booking ID (e.g. MN5V9DWQ)
lastName string Last name used when booking

Returns: Booking status, hotel name, room, check-in/check-out dates, price, cancellation policy, and confirmation link.


travala_cancel_booking

Cancel an existing booking.

Inputs:

Parameter Type Required Description
bookingId string Booking ID
lastName string Last name on the booking
email string Email address on the booking

Returns: Cancellation status, refund amount, cancellation fee, and policy summary.


Agent Registration & Rewards

Every travala_book call sends an agentId and rewardWallet to attribute the booking and route cbBTC giveback to your agent.

The skill file skills/travala-booking-expert/SKILL.md ships with both values empty by default. To earn rewards under your own agent identity, open that file and fill in the two lines with your own values:

agentId      = "your-agentId-from-8004scan"
rewardWallet = "0xYourEvmAddressOnBase"
  • agentId — self-register at 8004scan.io/agents to get an ID via the ERC-8004 registry. Travala does not issue these.
  • rewardWallet — any EVM address on Base (EOA, multi-sig, treasury contract). Does not have to be the wallet that pays for the booking.
  • Payout is made in cbBTC after the booking is marked completed (on or after guest check-in, subject to Travala's standard refund/cancellation window).

Without editing these values, bookings are attributed to the default agent and you earn nothing.


Typical flow

travala_search_hotel → travala_search_package → travala_book
                                                      ↓
                                          travala_manage_bookings
                                          travala_cancel_booking

                  (on book failure/timeout) → travala_book_status

Setup

Step 1 — Add Travala MCP

Claude Desktop

  1. Open Claude DesktopCustomizeConnectors
  2. Click +Add custom connector
  3. Fill in the popup:
    • Name: Travala MCP
    • Remote MCP Server URL: https://travel-mcp.travala.com/mcp
  4. Click Add — done.

Claude Code

Claude Code supports remote MCP servers natively. Run:

claude mcp add --transport http travala-mcp https://travel-mcp.travala.com/mcp

Or add manually to ~/.claude.json (user scope) or .mcp.json (project scope):

{
  "mcpServers": {
    "travala-mcp": {
      "type": "http",
      "url": "https://travel-mcp.travala.com/mcp"
    }
  }
}

Verify with claude mcp list.


Step 2 — Install Coinbase Agentic Wallet MCP (required for payment)

travala_book returns an HTTP 402 with x402 payment details. To complete the payment, you need @coinbase/payments-mcp installed alongside this server.

Prerequisite — Install Node.js

The npx command ships with Node.js. If you don't already have it, install Node.js (which includes npm and npx) before running the command below:

  • macOS / Linux / Windows: download the LTS installer from nodejs.org and follow the prompts.
  • macOS (Homebrew): brew install node
  • Verify installation: open a new terminal and run node -v and npx -v — both should print a version number.

Once Node.js is installed, run:

npx @coinbase/payments-mcp

When prompted, select your client (Claude for Desktop, Claude Code for CLI). The installer auto-configures the MCP entry. Restart your client after installation.


Step 3 — Install the booking skill

The travala-booking-expert skill ships rules and workflow logic. The agentId and rewardWallet fields are empty — fill them in if you want bookings attributed to your agent.

Before installing — fill in your values (optional, but required to earn rewards). Open skills/travala-booking-expert/SKILL.md and set agentId (from 8004scan) and rewardWallet (a standard EVM/ETH address on Base). See Agent Registration & Rewards above for the exact format.

Claude Desktop

Claude Desktop supports custom skills via .zip upload.

1. Enable Skills

  • Open Claude DesktopSettings
  • Go to Capabilities (or Features) and toggle Skills on if not already enabled

2. Zip the skill folder

The zip must keep the folder name at the top level:

travala-booking-expert.zip
└── travala-booking-expert/
    ├── SKILL.md          (required — metadata + instructions)
    └── references/       (optional — auto-loaded on demand)
cd skills && zip -r travala-booking-expert.zip travala-booking-expert/

3. Upload

  • Customize → Skills
  • Click +Create SkillUpload a Skill
  • Select travala-booking-expert.zip
  • Toggle the skill on in the list

Claude Desktop reads the skill description and auto-activates it when it matches the user's intent (e.g. "find me a hotel in Tokyo").

Claude Code

Copy the skill folder into your skills directory:

# Project-scoped (only this project)
cp -r skills/travala-booking-expert .claude/skills/

# OR user-scoped (all projects)
cp -r skills/travala-booking-expert ~/.claude/skills/

Claude Code auto-loads skills on startup. The references/ files come along automatically — the agent reads them on demand.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured