Is the Google BigQuery MCP server free?

Yes. Activepieces is open source and free to start, and the MCP server is included on every plan, from the free cloud tier to any self-hosted deployment.

How do I connect Google BigQuery to Claude or Cursor?

Connect Google BigQuery in Activepieces, enable the server under Settings → MCP Server, then paste your server URL into your client config. It authenticates over OAuth on first use.

What can my agent do in Google BigQuery?

It can call 10 tools, including Run a Query, Create Row, Create Rows, and chain them with steps in other apps inside the same run.

Is it safe to let an agent call Google BigQuery?

Connections use OAuth2 with limited scopes and are stored under 256-bit encryption, with no API to read them back, so an agent gets scoped access rather than your keys.

Google BigQuery MCP server

Query, analyze, and stream data into Google BigQuery — the fully managed, serverless data warehouse

Google BigQuery is not a separate install. One Activepieces MCP server exposes it alongside 760+ other apps, behind a single URL.

Start building See the Google BigQuery integration

Tools: 10
Works with: Any MCP client
Auth: OAuth 2.0 or Custom auth
License: MIT, open source
Updated: September 2026

About the Google BigQuery MCP server

Connect Google BigQuery once in Activepieces and every action it ships becomes a tool your assistant can call, behind the same server URL as the rest of your apps. Your agent reaches Google BigQuery and 760+ other apps over a single connection, on our cloud or a self-hosted install.

Tools

Google BigQuery tools your AI can run

Once connected, your assistant can call any of these Google BigQuery actions by asking in plain language.

Run a Query
Execute a SQL query on BigQuery and return the results as flat rows
5 fields
Create Row
Creates a single new row in a BigQuery table. Column fields are loaded from the table schema.
4 fields
Create Rows
Creates new rows of data in a BigQuery table (accepts an array of row objects). Rows are available to query within seconds.
6 fields
Delete Rows
Deletes one or more rows from a BigQuery table using a SQL WHERE condition.
5 fields
Update Row(s)
Updates one or more existing rows in a BigQuery table using SQL SET and WHERE expressions.
6 fields
Find One Row
Find a single row by specifying a WHERE clause and an optional ORDER BY. Returns the first matching row, or empty if none found.
6 fields
Find or Create Record
Searches for a row matching a WHERE clause. If found, returns it. If not found, inserts the provided row data and returns that.
6 fields
Get Rows for Job Completed
Retrieves the result rows from a completed BigQuery query job by Job ID. Use this after a "Query Job Completed" trigger to fetch the full result set.
4 fields
Import Data
Imports a batch of rows into a BigQuery table. Accepts a JSON array or newline-delimited JSON (NDJSON). Large datasets are automatically split into chunks.
6 fields
Custom API Call
Make a custom API call to a specific endpoint
10 fields

Triggers

Google BigQuery events your agent can watch

These start a run the moment something happens in Google BigQuery, so work gets picked up on its own.

New Row
Triggers when a new row is added to a BigQuery table. Polls every 5 minutes by comparing the latest value in a sort column against the previous check.
5 fields
Updated Row
Triggers when an existing row is updated in a BigQuery table. Requires an `updated_at` TIMESTAMP column that is set whenever a row changes.
6 fields
Query Job Completed (With Row Data)
Triggers when a BigQuery query job finishes successfully. Each flow run receives the job metadata and the result rows from that query.
2 fields
New Job Completed
Triggers when any BigQuery job (query, load, copy, or extract) finishes. Returns the job metadata including status, type, and timing.
2 fields

Give your assistant Google BigQuery

Connect Google BigQuery once and every tool above is callable from Claude, Cursor or any MCP client, behind the same server URL as 760+ other apps. Free to start.

Get your server URL Talk to sales

Google BigQuery MCP, answered.

No. That is the point of it. One Activepieces server exposes Google BigQuery alongside every other piece you connect, so your client keeps a single connection.