Travel
Cloudbeds MCP connector
The Cloudbeds connector brings group allotment blocks, folio adjustments, guest email templates and schedules, custom fields, property settings and dashboards to Claude, ChatGPT, Cursor and any MCP client, with every action tied to the person who signed in.
-
How it connects. Connects over OAuth. 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 Cloudbeds to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect Cloudbeds once
-
Open Connections, choose Add connection, and pick Cloudbeds.
-
Optionally set Share with to give a team access, then press Connect.
-
Supply your own Cloudbeds app, then approve. Cloudbeds needs an OAuth app you register yourself, so bring its client ID and secret. One person does this once for the organization.
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.
Connect Cloudbeds to 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.
Connect Cloudbeds to 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.
Connect Cloudbeds to 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 Cloudbeds 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 Cloudbeds through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
Group sales
Set up a group block once the contract signs
Create the allotment block in Cloudbeds with the agreed dates and room count, then add the notes from the contract so the front desk sees the terms without asking.
-
Reservations
Adjust a block when the group changes
Update the allotment block when the organizer adds rooms or shifts dates, and drop the block cleanly if the group cancels.
-
Front desk
Post a folio adjustment during checkout
Apply a credit for a maintenance issue or a correction for a misposted charge in Cloudbeds while the guest is still at the desk.
-
Finance
Reverse a batch of adjustments posted in error
Remove a set of mistaken adjustments in one pass instead of opening each folio, with a record of who did it and when.
-
Guest communications
Draft and schedule pre-arrival emails
Write a new email template for early check-in offers or parking instructions, then set the schedule so it goes out a set number of days before arrival.
-
Operations
Check settings and custom fields across properties
Pull the property settings, currency settings and custom fields for each hotel in Cloudbeds, spot the ones that drifted, and add a missing custom field where a property needs it.
Try asking
- “Which allotment blocks still have unsold rooms this weekend?”
- “Summarize adjustments posted against the Lisbon property yesterday.”
- “Add a note to the group allotment block for March.”
AI tools
Cloudbeds tools for your AI agents
555 tools are ready to call through Elaichi's MCP endpoint the moment you connect Cloudbeds, 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 Cloudbeds gets you
6 screens from the product, each doing one job for your Cloudbeds account.
The agent
Ask about tonight's allotment blocks in plain language.
Elaichi's agent answers from live Cloudbeds adjustments, allotment blocks and property settings.
- adjustments
- allotment blocks
- block notes
- property settings
Ask Elaichi to work across your apps.
Which allotment blocks still have unsold rooms this weekend?
Summarize adjustments posted against the Lisbon property yesterday.
Add a note to the group allotment block for March.
Also runs in Claude, ChatGPT or Cursor
MCP clients
Claude, ChatGPT and Cursor reach Cloudbeds here.
One org MCP endpoint over OAuth, no SDK and no shared API key.
Copy the endpoint
Tool catalog
555 Cloudbeds tools cataloged and ready to call.
Allotment blocks, adjustments, block notes and property settings, with no custom code written.
- List all Cloudbeds oauth metadata
- Create a Cloudbeds access token
- List all Cloudbeds userinfos
- Cloudbeds delete adjustments bulk delete
Toolboxes
Every team gets its own Cloudbeds toolbox.
Revenue, front desk and finance each see a toolbox curated for their work.
- Revenue management
- Front desk
- Finance
- Groups and events
Shared connections
Share a Cloudbeds property, never the credential.
The connections table shows who connected each account and which teams use it.
- Lisbon resort
- City hotels EMEA
- Groups and events
- Finance
Audit log
Every Cloudbeds call is written down.
When, who, what happened, type and resource, 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 fires, the digest posts back.
Cloudbeds adjustments are fetched, grouped, drafted by an agent, approved, then posted back.
Cloudbeds digest
Run 418 · started 2 minutes ago · on behalf of Emma Laurent
-
✓
Schedule
Every weekday at 08:00
0.2s -
✓
Fetch adjustments
Cloudbeds
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
Cloudbeds
Queued
Collections and dashboards
Cloudbeds numbers arrive before anyone asks.
Four metrics, 14 days of records created and a team breakdown, computed on schedule.
Cloudbeds health
Refreshed 4 minutes ago · every 15 minutes · from the adjustments collection
Adjustments
1,284 ↓ 12%
Allotment blocks
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Adjustments created
Last 14 days
By team
Share of activity
Lisbon resort 34%
City hotels EMEA 27%
Groups and events 21%
Finance 18%
Related connectors
More from the catalog
FAQ
Frequently asked questions
How do I connect Cloudbeds to Claude?
Two steps. First, connect Cloudbeds in Elaichi: Cloudbeds asks you to register an OAuth application in your own Cloudbeds account, so one person brings that client ID and secret once, then signs in to Cloudbeds and approves the connection. Second, in Claude open Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Claude then signs you in through Elaichi and Cloudbeds is available in your conversations.
Does Cloudbeds work with ChatGPT and Cursor as well as Claude?
Yes. Once Cloudbeds is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any other MCP client and the Elaichi Agent. You connect Cloudbeds once and every client you use picks it up.
What can an AI agent actually do with my Cloudbeds data?
It can create, update and remove group allotment blocks and their notes, post adjustments to folios or reverse a batch of them, read your dashboards, and look up property settings, currency settings and custom fields in Cloudbeds. It can also draft email templates and set email schedules for guest messages. Because Cloudbeds exposes several hundred actions, short concrete asks like "add two rooms to the Morgan wedding block" work better than long paragraphs.
Does connecting Cloudbeds give the AI access to all my properties?
No. Every action runs as the person who signed in to Cloudbeds, so the AI sees only the properties and settings that person can already reach. Elaichi can narrow that further, for example limiting a team to allotment blocks and email templates, but it never grants anything the person could not do in Cloudbeds directly.
Can I stop an agent from deleting or changing things in Cloudbeds?
Yes. Restrictions in Elaichi apply per action, so you can allow reading dashboards and property settings while blocking the removal of allotment blocks or the bulk deletion of adjustments in Cloudbeds. A blocked action is never shown to Claude, ChatGPT or Cursor at all, so no prompt, however worded, can reach it.
What happens to a Cloudbeds connection when someone leaves?
Offboarding that person in Elaichi ends their access to Cloudbeds through every client at once. A shared Cloudbeds connection keeps working for everyone else on the team. If you disconnect Cloudbeds in Elaichi, it disappears from Claude, ChatGPT, Cursor and every other client in one step.
Put Cloudbeds in front of your team
Fourteen days on Gold, no credit card. Connect it once and pick what each team can call.