Reads a table's schema and runs the SQL a question needs, creates datasets and streams in rows, cancels long-running jobs, and reports who has access.
63actions available
Every action runs live through MCP. Nothing to build, nothing to maintain.
Ayro runs a SQL query to pull the exact data you need from BigQuery in seconds. You get live results to answer customer questions without waiting for dashboard refreshes.
Ayro stops a long-running BigQuery query that's consuming resources or no longer needed. The job terminates immediately and frees up slots for other work.
Ayro launches a new query, load, or pipeline job in BigQuery asynchronously without blocking. Results arrive when the job completes so you can check them later.
Each card is one request a support team gets, and the Google BigQuery actions Ayro runs to close it.
Ayro fetches the table schema first so the query references real columns, runs the SQL, and returns the result rows, which keeps an ad-hoc data question from becoming a ticket for the analytics team.
Ayro creates the dataset in the right location, defines the table, and streams records into it one at a time, so a small feed can start collecting before anyone builds a load job for it.
Ayro lists the jobs started in a project, reports the configuration and status of the one someone is asking about, and cancels a query that is burning slots for no useful result.
Ayro reads the IAM policy on a table, lists the row access policies filtering what each caller sees, and tests which permissions the connected account itself holds on a routine.
How it works
Connect once, then just ask. There is no workflow builder to learn and nothing to maintain — Ayro reads the Google BigQuery actions it has and picks the ones a request needs.
Authorize the Google BigQuery account your team already uses — one consent screen, no API keys, no mapping tables. Ayro can only do what you granted that account, and you can disconnect it at any time.
Describe the job the way you would hand it to a teammate. Ayro maps it to the Google BigQuery actions that close it and chains as many as the request needs.
The agent runs the actions inside the conversation the customer is already in, so nobody copies data between tabs and your team can take over at any point.
Get started freeGoogle BigQuery · Ayro
What can you do in Google BigQuery without me setting anything up?
These, right away:
Great, let's start with the first one.
FAQ
Setup, permissions, and the limits of what Ayro can do inside Google BigQuery.
Insert BigQuery Job starts a query, load, extract, or copy asynchronously, Get BigQuery Job reports its status, and Get BigQuery Query Results fetches the rows once it completes. Cancel BigQuery Job returns immediately and the real state still has to be polled, so Ayro reports a cancellation as in progress rather than done.
All 63 actions your agent can call on Google BigQuery, straight from the live MCP connection.
Cancel a running BigQuery job.
Create a new capacity commitment resource in BigQuery Reservation.
Create a new BigQuery connection to external data sources using the BigQuery Connection API.
Create a new Analytics Hub data exchange for sharing BigQuery datasets.
Create a new listing in a BigQuery Analytics Hub data exchange.
Create a new BigQuery dataset with explicit location, labels, and description using the BigQuery Datasets API.
Create a new listing in a data exchange using Analytics Hub API.
Create a new data policy under a project with specified location using the v2beta1 BigQuery Data Policy API.
Create a new query template in a BigQuery Analytics Hub Data Clean Room (DCR) data exchange.
Create a new BigQuery reservation resource to guarantee compute capacity (slots) for query and pipeline jobs.
Create a BigQuery reservation assignment that allows a project, folder, or organization to submit jobs using slots from a specified reservation.
Create a new user-defined routine (function or procedure) in a BigQuery dataset.
Create a new, empty table in a BigQuery dataset.
Delete a BigQuery dataset specified by datasetId via the datasets.delete API.
Delete the metadata of a BigQuery job.
Delete a BigQuery ML model from a dataset.
Delete a BigQuery routine by its ID.
Delete a BigQuery table from a dataset.
Retrieve a specific BigQuery ML model resource by model ID.
Get the IAM access control policy for a BigQuery connection resource.
Retrieve BigQuery dataset metadata including location via the datasets.get API.
Retrieve information about a specific BigQuery job.
Get the results of a BigQuery query job via RPC.
Retrieve a BigQuery routine (user-defined function or stored procedure) by its ID.
Retrieve the IAM access control policy for a BigQuery routine resource.
Get the service account for a project used for interactions with Google Cloud KMS.
Retrieve the IAM access control policy for a BigQuery table resource.
Fetch a BigQuery table's schema and metadata without querying row data.
Stream data into BigQuery one record at a time without running a load job.
Start a new asynchronous BigQuery job (query, load, extract, or copy).
Same connection, same setup. Pick the next one your team already uses.
Runs a trained robot on demand or 1,000 tasks in one call, schedules change monitors, and reports what each extraction returned.
Runs a filtered statistics query against FaceUp reporting data so activity questions get a real figure in the conversation.
Reads the live data behind a dashboard, forces a stale data source to refresh, and manages the users, roles, and share rights around it.
Retrieves every scraping project on a ParseHub account, so a team confirms what is already configured without a dashboard login.
Records conversation events, updates customer traits, links anonymous visitors to known profiles, and reports source and destination delivery health.
Returns short, spoken or LLM-formatted computed answers, checks how a query parses, and recovers pods from a timed-out computation.

Authorize the account and your agent has all 63 actions from the first conversation.
