Weld
Start free

Toast Connector

Toast is a restaurant point of sale and management system that helps restaurants improve operations, increase sales and create a better guest experience.

Start for free
4.8 on G2
Weld · Data Sources
ToastLive
restaurantSynced
orderSynced
cash_entrySynced
service_areaSyncing
dining_optionQueued
Lands insnowflakebigquerydatabricksAgent context over MCP
How it works

Set up in minutes.
No code, no maintenance.

Toast

Toast

Data source

Authenticating...
Ready to connect
Overview

Toast in your warehouse.
Ready for your agents.

Toast is a restaurant point of sale and management system that helps restaurants improve operations, increase sales and create a better guest experience. Weld's Toast connector is fully managed: it extracts data from Toast, loads it into your warehouse, and keeps it in sync. The data lands in a clean, documented schema with agent context attached, so analysts can query it with SQL or dbt, and agents can query it over the Weld MCP server without guessing at tables or joins.

AgentsQuery over MCPYour warehouse67 tables, with agent contextWeldExtract, load, keep in syncToastSource
Agent context

Toast data schema.
The map your agents read.

Every table, field and relationship Weld syncs from Toast is served to agents as context over MCP, so they pick the right tables and join on the right keys.

tables
67
fields
1,021
relationships
47
Open the schema explorer Open the full schema explorer
Models

Toast models.
What the numbers mean.

Open-source SQL that turns the raw Toast tables into the reports people ask about. Deploy them in Weld and your agent queries the definitions, not guesses.

Open the models
Weld MCP server

Ask your agent.
It already knows Toast.

Connect Claude, Cursor, ChatGPT or your own agent to Weld over MCP. It reads the Toast context, finds the tables it needs and queries your warehouse.

  • Agent contextToast tables, fields and joins
  • QuerySQL against your warehouse
  • OperateCheck, rerun and refresh syncs
Set up the MCP serverClaudeCursorChatGPTGemini
Claude CodeOpus 5
>

How many menu_item_tax_rate rows do we have per tax_rate? Use our Toast data.

Reading the Toast context first, so the query uses the right tables and keys.

●weld·search_available_references
⎿raw.toast.menu_item_tax_rate
raw.toast.tax_rate
+ 65 more Toast tables
●weld·get_reference_schema
⎿menu_item_tax_rate · 6 columns
joins tax_rate on tax_rate_id
●weld·run_query
⎿select t.id, count(*) from {{raw.toast.menu_item_tax_rate}} m
join {{raw.toast.tax_rate}} t on m.tax_rate_id = t.id
group by 1
submitted
●weld·get_query_status
⎿DONE
●weld·get_query_result
⎿rows returned
✓Answered from Toast data in your warehouse
>Ask about your Toast data
Destinations

Load Toast into any warehouse.
Set up in minutes, no code.

Resources

Everything you need.
To get started.

MCP server

Connect your agents

Set up Claude, Cursor, ChatGPT or Codex against your Weld workspace.

Weld Connect API

Build custom connectors

Use the Weld Connect API to build and publish your own connector.

FAQ

Common questions

Answers to frequently asked questions about Weld connectors.

Weld Connect API

Set it up in code.
One REST API.

Use the Weld Connect REST API to create Toast connections, configure ELT syncs, and manage pipelines entirely through code. Built for embedding, automation, and CI/CD workflows.

Explore Weld ConnectAPI reference
POST/elt_syncs
▌
FAQ

Common questions.
About connectors.

Something not covered here? A data engineer can walk through your setup with you.

Talk to us

Put your Toast data to work.

Connect Toast, pick a warehouse, and your agents can query it today. Free for 14 days, no credit card.

ToastSource
WeldWeld
MCPAgents
Start for freeTalk to us
Connectors

Explore more connectors.
300+ and counting.

View all connectors