Toast MCP connector
Connect Toast to Elaichi and Claude, ChatGPT, Cursor, or any MCP client can read your restaurants' checks, orders, payments, menus, and payouts as the person who signed in, with every call 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 Toast to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect Toast once
-
Open Connections, choose Add connection, and pick Toast.
-
Optionally set Share with to give a team access, then press Connect.
-
Paste a Toast API key. One person generates a token in Toast 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.
Toast 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.
Toast 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.
Toast 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 Toast 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 Toast through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
Operations
Check on every restaurant before the huddle
Ask for last night's checks and payments across all your Toast restaurants and get one plain-language rundown before the morning meeting, without opening each location one at a time.
-
Finance
Reconcile payouts against payments
Pull the payouts, payout payments, and sales dates for a week and set them next to the guest payments Toast recorded, so the numbers that go to the accountant already match.
-
Kitchen
Compare menus across locations
List the menus at each restaurant, spot items and prices that drift between locations, and create a corrected price when the chef signs off.
-
Front of house
Find an open check fast
Ask which checks are still open at a restaurant, or open a new check for a walk-in group, while the manager is still on the floor.
-
People
Log labor and review shift coverage
Record a labor entry after a shift and list the week's labor by restaurant, so scheduling conversations start from what actually happened.
-
Leadership
Track metrics across the restaurant group
List the restaurants in a group alongside their orders and payments, and record a metric for the board pack without a spreadsheet in between.
Try asking
- “Total payments for the downtown restaurant last Friday”
- “Which menu items appear on the most open checks today?”
- “Summarize this week's payouts across all group restaurants”
AI tools
Toast tools for your AI agents
117 tools are ready to call through Elaichi's MCP endpoint the moment you connect Toast, 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 Toast gets you
6 screens from the product, each doing one job for your Toast account.
The agent
Ask about last night's checks in plain language.
Answers come from live Toast orders, payments, and menus, not from a stale export.
- checks
- orders
- payments
- payouts
Ask Elaichi to work across your apps.
Total payments for the downtown restaurant last Friday
Which menu items appear on the most open checks today?
Summarize this week's payouts across all group restaurants
Also runs in Claude, ChatGPT or Cursor
MCP clients
Toast in Claude, ChatGPT, and Cursor, connected once.
One governed endpoint for every MCP client, with no SDK and no shared API key.
Copy the endpoint
Tool catalog
117 Toast tools, ready without writing code.
Checks, orders, payments, menus, payouts, labor, and restaurants, covered from the first day.
- Create a Toast metric
- List all Toast metrics
- List all Toast restaurants informations
- Create a Toast check
Toolboxes
Every team gets its own Toast toolbox.
Finance sees payouts, kitchen sees menus, and each toolbox is scoped to one team.
- Operations
- Finance
- Kitchen
- Front of house
Shared connections
Share one Toast connection, never the API key.
One manager connects, teams and members work through it, and nobody sees a credential.
- Downtown
- Airport
- Catering
- Finance
Audit log
Every Toast call is logged with a name.
When, who, what happened, and which check or payment, 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 closes the day, a person approves.
Nightly checks are fetched, grouped by restaurant, drafted into a digest, approved, then posted to Toast.
Toast digest
Run 418 · started 2 minutes ago · on behalf of Emma Laurent
-
✓
Schedule
Every weekday at 08:00
0.2s -
✓
Fetch checks
Toast
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
Toast
Queued
Collections and dashboards
Toast sales health, computed without a model.
Four metrics, fourteen days of orders, and a breakdown by team, refreshed on a schedule.
Toast health
Refreshed 4 minutes ago · every 15 minutes · from the checks collection
Checks
1,284 ↓ 12%
Orders
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Checks created
Last 14 days
By team
Share of activity
Downtown 34%
Airport 27%
Catering 21%
Finance 18%
Related connectors
More from the catalog
FAQ
Frequently asked questions
How do I connect Toast to Claude?
First connect Toast in Elaichi by pasting a Toast API key. There is no OAuth application to register and no client ID or secret to generate. Then in Claude go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp as the endpoint. Sign in with your Elaichi account and Toast is available in your next conversation.
Does Toast work with ChatGPT and Cursor as well as Claude?
Yes. Once Toast 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 Toast once and every client picks it up.
What can an AI agent actually do with my Toast data?
With Toast connected, an agent can list your restaurants, pull checks, orders, payments, and payouts for a location or a date range, read the menus at each site, and record new checks, labor entries, prices, payouts, and metrics on your behalf. Short, concrete asks like "payments at the downtown restaurant yesterday" work better than long paragraphs.
Does connecting Toast give the AI access to every restaurant?
No. Every call to Toast runs inside the access of the person who signed in, so an agent can only see the restaurants and records that person can already see in Toast. Elaichi can narrow that further with roles and restrictions, and it can never widen it.
Can I stop an agent from deleting or changing things in Toast?
Yes. Restrictions in Elaichi work per action, so you can allow reading checks and payments while blocking anything that creates a check, a price, or a payout in Toast. A restricted action is never advertised to Claude, ChatGPT, or Cursor at all, so no prompt can reach it.
What happens to a Toast connection when someone leaves?
Offboarding a person in Elaichi ends their access to Toast at once, in every client they used. A Toast connection they shared with the team keeps working for everyone else. If you want it gone entirely, disconnecting Toast once in Elaichi removes it from Claude, ChatGPT, Cursor, and every other client together.
Does the Toast MCP connector work with Gemini, Codex, Claude Code or other MCP clients?
Yes. Toast 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 Toast 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.