Travefy MCP connector
Connect Travefy to Elaichi and Claude, ChatGPT, Cursor, or any MCP client can look up and update your bookings, contacts, traveler preferences, loyalty programs, and library content, with every call running as the signed-in advisor and logged.
-
How it connects. Connects with an API key. The credential goes into a vault nobody reads back.
-
One address. https://api.elaichi.ai/mcp, the same for every user.
-
Their own access. An agent never gets more than the person it acts for.
How to connect
How to connect Travefy to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect Travefy once
-
Open Connections, choose Add connection, and pick Travefy.
-
Optionally set Share with to give a team access, then press Connect.
-
Paste a Travefy API key. One person generates a token in Travefy and pastes it once. Everyone else works through Share with, and never sees it.
The credential is vaulted. Nobody reads it back, not even the AI.
Add connection
Choose a connector.
In your AI client
Point it at one endpoint
Everyone in the organization uses the same address, and each person only ever reaches what their own account allows.
Travefy MCP connector for Claude
-
1
Open Customize, then Connectors.
-
2
Press Add.
-
3
Name it, paste the MCP server URL, then Continue.
https://api.elaichi.ai/mcp -
4
Sign in and approve.
On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.
Travefy MCP connector for ChatGPT
-
1
Open Plugins, then press the + button.
-
2
Name it and paste the endpoint into Server URL.
https://api.elaichi.ai/mcp -
3
Leave Authentication on OAuth, then tick the risk acknowledgement.
-
4
Press Create, then sign in and approve.
Works on the web today. The plugin directory lives at chatgpt.com/plugins.
Travefy MCP connector for Cursor
-
1
Open
~/.cursor/mcp.json. -
2
Add the endpoint under
mcpServers.https://api.elaichi.ai/mcp -
3
Reload Cursor, then sign in and approve.
~/.cursor/mcp.json
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
Set up per machine, so repeat it on each computer you work from.
Connect Travefy to any MCP client
-
1
Add the endpoint as a remote MCP server.
https://api.elaichi.ai/mcp -
2
Sign in and approve.
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
The Elaichi Agent already has these tools, with nothing to set up.
Use cases
What teams do with Travefy through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
Travel advisors
Catch a contact up after a discovery call
Tell the agent what you learned on the call and it updates the Travefy contact, including the custom fields your agency tracks, so the record matches the conversation before you build the proposal.
-
Operations
See every booking departing this month
Ask for the Travefy bookings leaving in the next thirty days and get a plain list you can work through, then update any booking whose dates or details have shifted.
-
Client services
Check preferences before you book
Pull a traveler's stored preferences and loyalty programs from Travefy in one ask, so seat choices, room types, and frequent flyer numbers make it onto the booking the first time.
-
Agency owners
Clean up duplicate and stale contacts
Have the agent list Travefy contacts that look like duplicates, merge the details into the right record, and remove the leftovers, with each change recorded in the log.
-
Marketing
Refresh the content library for a new season
Add fresh hotel and destination descriptions to your Travefy library and clear out last season's entries in bulk, so advisors are building itineraries from current material.
-
Sales
Turn a confirmed proposal into a booking
When a client says yes, ask the agent to create the Travefy booking with the traveler, dates, and details already in the contact record, instead of retyping them.
Try asking
- “Which Travefy bookings depart in the next two weeks?”
- “Show Maria Lopez's traveler preferences and loyalty programs.”
- “Update the anniversary field for every contact traveling in June.”
AI tools
Travefy tools for your AI agents
88 tools are ready to call through Elaichi's MCP endpoint the moment you connect Travefy, governed by the same roles, restrictions, and audit log as everything else in Elaichi.
No tools match your search.
See it in Elaichi
What connecting Travefy gets you
6 screens from the product, each doing one job for your Travefy account.
The agent
Ask about Travefy bookings in plain language.
Answers come from live Travefy bookings, contacts, and traveler preferences, not from memory.
- bookings
- contacts
- custom fields
- library contents
Ask Elaichi to work across your apps.
Which Travefy bookings depart in the next two weeks?
Show Maria Lopez's traveler preferences and loyalty programs.
Update the anniversary field for every contact traveling in June.
Also runs in Claude, ChatGPT or Cursor
MCP clients
One endpoint brings Travefy to every client.
Claude, ChatGPT, and Cursor reach Travefy through one governed endpoint, no SDK, no shared key.
Copy the endpoint
Tool catalog
88 Travefy tools, ready without any code.
Bookings, contacts, custom fields, and library content, covered with no custom code.
- List all Travefy bookings
- Create a Travefy booking
- Get single Travefy booking by ID
- Update a Travefy booking by ID
Toolboxes
Every team gets its own Travefy toolbox.
Advisors, operations, and marketing each work from a toolbox scoped to their job.
- Advisors
- Operations
- Client services
- Marketing
Shared connections
Share Travefy without sharing the API key.
One person connects Travefy, teammates book and update contacts without seeing a credential.
- Luxury desk
- Group travel
- Corporate
- Honeymoons
Audit log
Know who changed every Travefy booking.
When, who, what happened, and which booking or contact, in an append-only log.
- When
- Who
- What happened
- Type
Launching soon
From answering questions to doing the work
A person no longer has to ask. A trigger starts the work, inside the same permissions and the same audit log as everything else. Automations and live dashboards are launching soon, on the Black plan.
Automations
A schedule turns Travefy bookings into work.
Departures are fetched, grouped, drafted into a digest, approved by a person, then posted back.
Travefy digest
Run 418 · started 2 minutes ago · on behalf of Emma Laurent
-
✓
Schedule
Every weekday at 08:00
0.2s -
✓
Fetch bookings
Travefy
1.4s -
✓
Group by owner
Transform
0.1s -
✓
Draft the digest
Agent step
Ran with 4 tools, returned a structured summary
6.2s -
Approve the digest
Needs approval
Assigned to Michael Brennan
Approve Deny -
Post the digest
Travefy
Queued
Collections and dashboards
Travefy numbers, computed without a model.
Bookings created over 14 days, broken down by team, refreshed on a schedule.
Travefy health
Refreshed 4 minutes ago · every 15 minutes · from the bookings collection
Bookings
1,284 ↓ 12%
Contacts
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Bookings created
Last 14 days
By team
Share of activity
Luxury desk 34%
Group travel 27%
Corporate 21%
Honeymoons 18%
Related connectors
More from the catalog
FAQ
Frequently asked questions
How do I connect Travefy to Claude?
In Elaichi, choose Travefy and paste the API key from your Travefy account, then open Claude, go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. There is no OAuth application to register and no client ID or secret to generate. Once Travefy is connected, sign in to Elaichi from Claude and you can start asking about bookings and contacts.
Does Travefy work with ChatGPT and Cursor as well as Claude?
Yes. Travefy is connected once in Elaichi, and the same endpoint, https://api.elaichi.ai/mcp, is added to Claude, ChatGPT, Cursor, any other MCP client, and the Elaichi Agent. You do not connect Travefy separately for each client.
What can an AI agent actually do with my Travefy data?
With Travefy connected, an agent can list, create, update, and remove bookings and contacts, read a traveler's preferences and loyalty programs, fill in and bulk update contact custom fields, and add or clear out library content. Short concrete asks work best, such as which bookings depart next week or update this contact's passport expiry. The agent cannot do anything with Travefy beyond those tasks.
Does connecting Travefy give the AI access to every booking and contact in the agency?
No. Every call to Travefy runs under the API key and access of the person who connected it in Elaichi, so the agent sees what that person sees in Travefy and nothing more. Elaichi can narrow that access further, for example to reading only, but it can never widen it beyond what Travefy already allows.
Can I stop an agent from deleting or changing things in Travefy?
Yes. In Elaichi, each Travefy action can be restricted on its own, so you can allow reading bookings and contacts while blocking deletion or edits. A restricted action is never advertised to Claude, ChatGPT, Cursor, or any other client, so no prompt can reach it.
What happens to a Travefy connection when someone leaves?
Offboarding a person in Elaichi ends their access to Travefy at once, in every client they used. A Travefy connection shared with the team keeps working for everyone else. If you ever want Travefy gone entirely, disconnecting it once in Elaichi removes it from Claude, ChatGPT, Cursor, and every other client at the same time.
Does the Travefy MCP connector work with Gemini, Codex, Claude Code or other MCP clients?
Yes. Travefy is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.
Put Travefy in front of your team
14 days on Gold, no credit card. Connect it once and pick what each team can call.
- Works with
-
and any other MCP client, or the Elaichi Agent.
- When the trial ends
- Nothing is deleted. Connections, roles and the audit log stay where they are, so subscribing picks up exactly where you left off.