Integration · Research and analyze

Coupler.io and Meteor AI agents

Connect Coupler.io to a Met: query your data flows' data sets with SQL, build new ones and refresh the data with the official MCP.

Book a demo See every integration

How does Coupler.io connect to Meteor?

With the Coupler.io ready connector, your Met queries the data sets of the data flows you have in Coupler.io, the ones that bring together data from your sources, such as your store and your ads, with 24 tools. It reads the columns and the saved business context, runs the SQL query on Coupler.io's side and replies with the result. It can also build new data sets, create or adjust data flows, save what it learned about a data set and refresh a data flow from its source. Queries do not change the imported rows. Your Coupler.io plan pays for the service.

What it automates

What a Meteor Met does with Coupler.io

Answer with your data

You ask the Met on WhatsApp how much you sold yesterday. The Met finds the data set, reads its columns and runs the SQL query in Coupler.io, which returns only the result.

Combine two data sets

If the question needs sales and ads from the same data flow together, the Met builds a new SQL data set with the join or aggregation, because each query reads one data set at a time.

Remember the business context

The Met saves what it learned on the data set, such as that the currency is COP or which rows to exclude, so the next conversation starts informed.

Build a new data flow

The Met checks which services you already authorized, creates the data flow empty or from a template and adds the source and the destination.

Refresh before replying

If you ask for today's data, the Met checks when the data flow last ran and, if you ask it to, refreshes it from its source.

24 tools

Everything your Met can ask Coupler.io for

Each one is a real action in the connector. You can switch off the ones you would rather it never used.

Tool	What it does
`list_datasets`	Lists the data sets across all your data flows, to answer "what data do I have?".
`search_datasets`	Finds a data set by name, source or keyword.
`list_templates`	Browses Coupler.io's ready-made templates to suggest a pre-built setup.
`get_schema`	Reads a data set's columns, with their names, types, descriptions and saved business context.
`get_data`	Runs a SQL query against a data set and returns the result; the query runs on Coupler.io's side.
`create_dataset`	Builds a new SQL data set from data sets in the same data flow, with a join, an aggregation or a pivot.
`update_dataset_query`	Changes the SQL behind an existing SQL data set.
`update_dataset_schema`	Improves the column labels and descriptions.
`create_dataflow`	Creates an empty data flow to attach a source and a destination to.
`create_dataflow_from_template`	Creates a data flow from a template, already configured.
`get_dataflow`	Reports a data flow's state, with its sources, destinations and last run.
`create_dataflow_source`	Adds the source the data is pulled from.
`update_dataflow_source`	Changes the source the data is pulled from.
`create_dataflow_destination`	Adds the destination where the data is delivered.
`update_dataflow_destination`	Changes the destination where the data is delivered.
`update_dataflow`	Renames a data flow, or changes and pauses its schedule.
`list_credentials`	Checks which services you already authorized and gives a link to connect a new one.
`list_integrations`	Lists the services Coupler.io supports as a source or a destination.
`get_integration`	Reads what an integration needs, with its parameters and how it authenticates.
`get_integration_field_options`	Fills in the choices for a setting that depends on your account, such as which ad account or which spreadsheet.
`update_dataset`	Saves what was learned about a data set as business context, such as what a metric means, its currency or which rows to exclude.
`run_dataflow`	Refreshes a data flow from its source.
`list_skills`	Checks which Coupler.io skills are available for your workspace.
`get_skill`	Loads a skill's instructions to follow a proven procedure.

The limits

What the Coupler.io integration does NOT do

We would rather say it here than have you find out during rollout.

It does not edit, delete or overwrite the rows Coupler.io imported: queries are read only. What it can change is the configuration of your data flows, sources, destinations, schedule, columns and SQL data sets.
It does not see data flows that do not have the MCP as a destination. A tool connected over MCP only sees the data sets of data flows with that destination; if it is missing, it is added in Coupler.io, which lists Custom MCP among its AI destinations.
It does not ask you for confirmation in the chat before writing: the admin decides in Connections which actions stay on.
It sees nothing beyond those data sets: not your other accounts and not your computer.
It does not pay your Coupler.io plan. Meteor does not resell the service.

Before you start

What you need to connect Coupler.io

1

A Coupler.io account with your data flows

The data the Met queries lives in Coupler.io data flows, which bring in data from your sources, such as your store and your ads. They can also be built from the conversation.
2

Connect it in Met

In Met, open Connections → Coupler.io → Connect. A Coupler.io window opens so you sign in and authorize Met. You connect once and there are no API keys to manage.
3

The MCP destination on each data flow

For the Met to see a data set, its data flow has to have the MCP as a destination. That destination is added in Coupler.io.