Integration

Google BigQuery integration

Google Cloud's serverless data warehouse for analytics. Run SQL queries, manage datasets, tables, and jobs. Supports streaming inserts, table operations, and query result retrieval at petabyte scale.

Connect Google BigQuery How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Google BigQuery.Built from the 19 Google BigQuery tools below, on the connection you add once.

Common Google BigQuery use cases

real-time event logging
stopping runaway queries
monitoring active queries
previewing table contents
removing temporary tables
polling for job completion
setting up new data domains
updating dataset descriptions
cleaning up temporary datasets
discovering available datasets

What you can do with Google BigQuery

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Table, 7 operations

create_tableCreate tablePOSTCreates a new BigQuery table with a defined schema, optional partitioning, clustering, and expiration. Returns the created table metadata including its full reference and schema.
delete_tableDelete tableDELETEPermanently deletes a BigQuery table and all its data. This operation cannot be undone. Time travel (7-day window) may allow recovery via table snapshot if configured.
get_tableGet tableGETRetrieves full metadata for a BigQuery table including schema definition, row count, byte size, partitioning, clustering, streaming buffer status, and expiration time.
insert_rowsInsert rowsPOSTStreams rows into a BigQuery table for near real-time data availability. Rows are available for querying within seconds. Supports batch inserts with optional deduplication via insertId.
list_table_dataList table dataGETReads rows from a BigQuery table without running a query job. Returns data in insertion order with pagination support. Faster than queries for simple full-table reads.
list_tablesList tablesGETLists all tables, views, and materialized views in a BigQuery dataset. Returns table references, type (TABLE, VIEW, MATERIALIZED_VIEW, EXTERNAL), row count, size, and creation time.
update_tableUpdate tablePUTUpdates metadata for a BigQuery table. Add new columns to the schema, modify description, friendly name, expiration, and labels. Cannot remove or rename existing columns.

Dataset, 5 operations

create_datasetCreate datasetPOSTCreates a new BigQuery dataset in the specified project. Configure location, description, table expiration defaults, and labels. Location is permanent and cannot be changed after creation.
delete_datasetDelete datasetDELETEDeletes a BigQuery dataset. By default fails if tables exist. Set deleteContents=true to recursively delete all contained tables, views, and routines along with the dataset.
get_datasetGet datasetGETRetrieves full metadata for a BigQuery dataset including access controls, default table expiration, location, labels, description, and encryption configuration.
list_datasetsList datasetsGETLists all datasets within a BigQuery project. Returns dataset IDs, friendly names, locations, and labels. Supports filtering by labels and pagination.
update_datasetUpdate datasetPUTUpdates metadata for an existing BigQuery dataset. Modify friendly name, description, default table expiration, labels, and access controls. Location cannot be changed.

Job, 4 operations

cancel_jobCancel jobPOSTCancels a running BigQuery job. Cancellation is best-effort; the job may complete before the request is processed. Returns the final job state after cancellation attempt.
get_jobGet jobGETRetrieves metadata and status for a BigQuery job. Returns configuration, current state (PENDING, RUNNING, DONE), error details if failed, and execution statistics including bytes processed and slot time.
insert_jobInsert jobPOSTCreates an asynchronous BigQuery job for queries, loads, extracts, or copies. Returns a job reference immediately while work runs in the background. Use get_job to poll for completion and get_query_results to fetch results.
list_jobsList jobsGETLists BigQuery jobs for a project with filtering by state and user. Returns job references, status, statistics, and configuration. Supports pagination for projects with many jobs.

Query, 2 operations

get_query_resultsGet query resultsGETRetrieves query results for a completed or in-progress BigQuery job. Supports pagination through large result sets using pageToken or startIndex. Returns rows, schema, and completion status.
run_queryRun queryPOSTExecutes a BigQuery SQL query synchronously and returns results inline. Use for quick queries expected to finish within the timeout. Returns rows, schema, and job reference. For long-running queries, use insert_job with a query configuration.

Project, 1 operation

list_projectsList projectsGETLists all GCP projects accessible to the authenticated user via BigQuery. Returns project IDs, numeric IDs, and friendly names. Essential for discovering available projects before other operations.

OAuth scopes Google BigQuery requires

Each operation declares the scopes Google BigQuery requires for it.

https://www.googleapis.com/auth/bigqueryneeded by cancel_job, create_dataset, create_table and 16 more

Use Google BigQuery from Claude Code, Cursor or Codex

Connect Google BigQuery in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Google BigQuery operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Google BigQuery

Create your workspace
Sign up free. Nothing to install.
Connect Google BigQuery once
Add your Google BigQuery connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

Google BigQuery integration FAQ

What can you do with the Google BigQuery integration?

LiveContext exposes 19 operations on Google BigQuery, covering table, dataset, job and query. Common uses include real-time event logging, stopping runaway queries and monitoring active queries.

Which OAuth scopes does Google BigQuery require?

The operations that declare a scope all need https://www.googleapis.com/auth/bigquery.