Connect Google BigQuery to Claude Code
Give Claude Code governed access to Google BigQuery’s 9 tools through Runlayer, with identity, policy, scanning, and audit on every call.
Set up
Add Google BigQuery to Claude Code in four steps
Admins approve the server once. Everyone in Claude Code then gets it through the same governed connection.
- 1
Approve Google BigQuery in Runlayer
Add Google BigQuery from the catalog and choose who can use it and which of its tools are allowed.
- 2
Connect Claude Code to Runlayer
Runlayer’s CLI installs the Runlayer Plugin natively in Claude Code, and an Anthropic org install also reaches Claude Code. With direct tool listing turned on for your deployment, Google BigQuery’s 9 tools show up in Claude Code’s own tool list (supported Claude Code versions).
Claude Code setup guide - 3
Sign in to Google BigQuery
Each user signs in to Google BigQuery with OAuth. Runlayer keeps the tokens out of the client’s configuration.
- 4
Use Google BigQuery from Claude Code
Google BigQuery’s approved tools appear in Claude Code. Every call is checked against policy and recorded.
Tools
9 Google BigQuery tools in Claude Code
Runlayer policy decides which of these Claude Code users can call.
Cancel job
Cancel a running BigQuery job.
Execute SQL
Run a SQL query in the project and return the result.
Execute SQL readonly
Run a read-only SQL query in the project and return the result.
Get dataset info
Get metadata information about a BigQuery dataset or BigLake namespace.
Get job
Get information and status about a BigQuery job.
Get query results
Get the results of a BigQuery SQL query job.
Get table info
Get metadata information about a BigQuery table or BigLake table.
List dataset IDS
List BigQuery dataset IDs and BigLake namespaces in a Google Cloud project.
Control
What Runlayer can see and stop in Claude Code
Some controls apply to every client at the gateway. Others depend on what Claude Code exposes to Runlayer.
Gateway policy (available)
Every Google BigQuery call from Claude Code passes through Runlayer, where your policies can allow, alert, mask, or block it.
Audit trail (available)
Each call is recorded with the user, Claude Code as the client, the tool, and the policy and scanner decisions.
Client hooks (available)
Capture supported prompts, reasoning, local and MCP tool calls, responses, and scanner decisions in real time.
Anthropic inference hooks (available)
With Claude Enterprise, Anthropic sends each governed Claude Code prompt to Runlayer before inference, with nothing installed on devices (Anthropic beta).
OTLP telemetry (available)
Claude Code can export OpenTelemetry logs to Runlayer for observe-only session reconstruction.
Stop a call before it runs (available)
Runlayer can deny a tool call before Claude Code runs it.
Block output after it runs (available)
Runlayer can block a tool’s output before Claude Code’s model sees it.
Redact output in place (available)
Runlayer can mask sensitive parts of a tool’s output in Claude Code and pass the rest through.
In Claude Code
- When a tool fails, Runlayer records the error but cannot hide it.
Frequently asked questions
Connect more