# Autonomad1/autonomad-travel [Health: Active]

**Category:** 🚆 Travel & Transportation  
**Repository:** https://github.com/Autonomad1/autonomad-travel  
**GitHub Stars:** 2  
**npm Downloads (last month):** 551  
**Views:** 4  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/autonomad1-autonomad-travel

## Description
AI travel agent over MCP — live flights, hotels, activities, and events worldwide, then completes the booking on autonomad.ai (free signup at checkout, first month of Premium included).

## Tools
Capabilities this server exposes over MCP:

- **search_hotels** — Search hotels, lodging, accommodations, resorts, and places to stay for a trip. Filter by city, country, check-in/check-out dates, room type, nightly price, star rating, and amenities (pool, gym, wifi, etc.). Returns matching properties with rates, photos, and availability across 2M+ properties (LiteAPI). Use this when the user wants to book a hotel, find a place to stay, compare lodging options, or pick a resort.
- **search_flights** — Search airline flights / airfares between two cities by date, cabin class (economy / premium economy / business / first), and number of passengers. Returns available flights from 800+ airlines (Duffel) with real-time pricing, schedules, and stops. Uses IATA airport codes (e.g., MIA, JFK, LAX, LHR). Use this when the user wants to book a flight, fly somewhere, find airfare, or compare airlines.
- **search_dining** — Search restaurants and dining options by city, date, time, cuisine, party size, neighborhood, and price range. PLANNING ONLY — this returns restaurant details and indicative availability; Autonomad does not place reservations, and the user completes any booking with the restaurant directly. Use this when the user wants to find, compare, or shortlist somewhere to eat on a trip.
- **search_activities** — Search tours, experiences, attractions, sightseeing, and things to do via Viator (200K+ activities worldwide). Filter by city, date range, and category (food tours, walking tours, museums, snorkeling, sailing, hiking, sunset cruises, cooking classes, day trips, etc.). Returns activities with photos, ratings, durations, and per-person pricing. Use this when the user wants to plan day activities, find tours, book experiences, fill a trip itinerary, or pick attractions.
- **search_events** — Search live events, concerts, sports games, theater, comedy, and shows in a city (Ticketmaster + SeatGeek catalog). Filter by city, date range, category (music / sports / arts / theater / family / comedy), and keyword (artist name, team name, show title). Use this when the user wants tickets to a concert, a sports game, a Broadway show, or any live event during their trip.
- **create_booking_intent** — Create a booking intent — returns a deep-link the user clicks to complete the booking on autonomad.ai. Signing up is free, with no trial and no subscription. ALWAYS call this instead of trying to book directly through MCP — bookings require payment + identity verification that must happen on the web. 

WHEN TO CALL — two distinct triggers:
  (a) PICK intents (flight / hotel / activity / event / trip): call AFTER the user has chosen a specific offer.
  (b) BROWSE intent ('experiences'): call IMMEDIATELY in the SAME assistant turn that you ran search_activities and/or search_events for a browse query. Do NOT wait for the user to ask 'where's the link?' — the user already told you they want this when they asked to browse. Showing search results without also producing the deep-link is a UX failure: it forces the subscriber to manually request something they already implicitly asked for.

INTENT TYPE GUIDE — pick exactly one:
- 'flight'   → user picked a flight only. offer_data = the flight offer object verbatim from search_flights, PLUS a top-level `passengers: <number>` field (the number of travelers the user originally requested — search_flights individual offers don't echo this back, so you must add it explicitly).
- 'hotel'    → user picked a hotel only. offer_data = the hotel offer object verbatim from search_hotels (or just {city, check_in, check_out} if you want to send them to a hotel-search results page rather than a specific hotel). Include `adults: <number>` and `rooms: <number>` so the booking page pre-fills the right party size.
- 'activity' → user picked a Viator activity. offer_data = the activity offer.
- 'event'    → user picked a Ticketmaster/SeatGeek event. offer_data = the event offer.
- 'trip'     → user picked MULTIPLE things together (e.g. flight + hotel for the same trip). Pack them in offer_data as { flight: { ...offer, passengers: <n> }, hotel: { ...offer, adults: <n>, rooms: <n> }, activities: [<activity_offer>, ...] } — only include the keys the user actually picked. ONE deep-link covers all of them.
- 'experiences' → BROWSE intent. The user wants to look at all activities AND events for a destination + date window WITHOUT picking a specific one. STRONGLY PREFER this over picking one activity yourself when the user asks to 'browse', 'see what's available', 'look at experiences in X', or just describes a destination/date range with no specific tour name. offer_data shape: { destination: 'City, Region', date_from: 'YYYY-MM-DD', date_to: 'YYYY-MM-DD', travelers?: <number>, activity_keywords?: [...], event_categories?: [...] }. The deep-link lands the subscriber on autonomad.ai's add-ons step with destination + dates pre-filled, where Viator activities and Ticketmaster/SeatGeek events for the area are surfaced together — and they can edit dates / traveler count inline. Use this whenever the subscriber's intent is 'show me everything', not 'I want this one specific tour'.

Prefer 'trip' when the user said something like 'book me a flight and hotel for X' and you have both picked. Prefer 'experiences' when the user is asking to BROWSE activities/events without picking one (e.g. 'experiences between July 9 and July 13 near Stintino' → ONE deep-link, not 24 individual activity intents). Don't generate two separate intents (flight + hotel) for the same trip — that produces two deep-links and a confusing user experience.

USER-FACING REPLY REQUIREMENTS — every time you create a booking intent, your reply text MUST include:
1. The deep_link as a clickable markdown link, e.g. '[Complete on autonomad.ai →](<deep_link>)' or 'Open: <deep_link>'.
2. That the account is free. Autonomad costs the traveller nothing — no subscription, no trial, no card required to sign up; they pay only for the travel they book. NEVER describe a trial, a free month, or Premium: none of those exist, and promising one is a claim we cannot honour.
3. The link expiry window (e.g. '~30 minutes — say the word and I'll regenerate if it lapses.').

CRITICAL: always echo the original passenger / adults / travelers count into offer_data. Without it the booking page defaults to 2 travelers regardless of what the user asked for.
- **get_capabilities** — Return the server's version, mode (human vs autonomous-agent), API base, and the list of currently-exposed tools. Useful for the LLM to confirm tool-schema compatibility before issuing a sequence of calls — call once at session start if you need to branch on capabilities.

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `npx` (confidence: high):

```json
"mcpServers": {
  "autonomad-travel": {
    "command": "npx",
    "args": ["-y","autonomad-travel"],
    "env": {
      "AGENT_DID": "",
      "BOOKING_API_URL": "",
      "IDENTITY_API_URL": "",
      "REWARD_API_URL": ""
    }
  }
}
```

**Requires environment variables:** `AGENT_DID`, `BOOKING_API_URL`, `IDENTITY_API_URL`, `REWARD_API_URL` — the values above are empty placeholders; fill in real credentials before running (see the repository for what each one is for).

## Documentation

## What Autonomad1/autonomad-travel does

Autonomad1/autonomad-travel MCP server exposes travel search and trip-management functions to MCP-compatible agents. It connects agents to live inventory for hotels, flights, activities, events, car rentals, and selected dining and rideshare workflows. The service is intended for agents that need to plan real trips and hand users a path to complete booking, or manage bookings after they are created.

Hotel search covers more than 2 million properties and can return prices, photos, amenities, availability, and cancellation terms. Flight search covers more than 800 airlines and provides schedules, current pricing, and fare comparisons. Activities use the Viator Partner API, while events are sourced from Ticketmaster and SeatGeek. Car rental search is available in more than 15 US metropolitan areas. Rideshare and dining partnerships are still in progress.

## How it works

Autonomad1/autonomad-travel can be launched as a local stdio process and connected to an MCP client. The README also identifies a hosted MCP endpoint at `mcp.autonomad.ai/mcp`, which is already available through the Autonomad connector for Claude and ChatGPT. Local deployments use the booking, identity, and rewards API endpoints configured in the environment.

The server provides tools for individual searches as well as broader orchestration. `manage_trip` can plan, monitor, and adapt a multi-leg itinerary, including responses to disruptions. Hotel reservations are created with `create_booking`, while `manage_booking` supports check-in, check-out, and cancellation workflows. An agent DID is used for autonomous-agent booking authority and rewards attribution; human travelers using the hosted connector do not need to register one.

## Setup and configuration

Run the server once with:

```bash
npx -y autonomad-travel
```

It can also be installed globally with npm and started using the `autonomad-travel` executable. `AGENT_DID` is required for bookings and can be registered through autonomad.ai. The API URL defaults to `https://api.autonomad.ai`.

Additional configuration variables are available for identity resolution and reward settlement: `IDENTITY_API_URL` and `REWARD_API_URL`. Both default to the same Autonomad API host. The project is licensed under MIT.

## Tools and capabilities

Autonomad1/autonomad-travel exposes these MCP tools:

- `search_hotels`: Find available hotels with commercial and property details.
- `search_flights`: Compare live flight schedules, fares, and airlines.
- `book_transport`: Find itinerary-timed car rental and rideshare quotes.
- `book_dining`: Search restaurants that fit the trip schedule.
- `manage_trip`: Coordinate, monitor, and adjust complete itineraries.
- `create_booking`: Reserve hotel rooms with commission and delegation details.
- `manage_booking`: Handle check-in, check-out, and cancellation actions.
- `submit_feedback`: Send structured post-stay reviews for travel categories.
- `check_rewards`: Query `$NOMD` balances, settlement history, and redemption options.

It also exposes `autonomad://hotels` for hotel catalog and live availability data, plus `autonomad://profile` for the agent profile, reputation score, and tier status.

## Limitations and notes

Coverage is not uniform across all travel categories. Car rental is limited to the listed US metro coverage, while rideshare and dining integrations are described as in progress. Wellness is marked as coming soon.

Rewards depend on completed bookings and use the Autonomad agent identity and settlement system. The `$NOMD` reward, tier, and redemption features are therefore relevant mainly to autonomous agents with a registered DID, not just read-only search clients.

_Full upstream README: https://allmcps.com/mcp/autonomad1-autonomad-travel/readme_