Skip to main content

Connect Google BigQuery to Hermes

Give Hermes 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 Hermes in four steps

Admins approve the server once. Everyone in Hermes then gets it through the same governed connection.

  1. 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. 2

    Connect Hermes to Runlayer

    Users add the Runlayer Plugin to Hermes by following Runlayer’s setup guide. Hermes reaches Google BigQuery’s 9 tools through the Runlayer Plugin’s search and execute tools instead of listing each one.

    Hermes setup guide
  3. 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. 4

    Use Google BigQuery from Hermes

    Google BigQuery’s approved tools appear in Hermes. Every call is checked against policy and recorded.

Tools

9 Google BigQuery tools in Hermes

Runlayer policy decides which of these Hermes 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.

See all 9 Google BigQuery tools

Control

What Runlayer can see and stop in Hermes

Some controls apply to every client at the gateway. Others depend on what Hermes exposes to Runlayer.

  • Gateway policy (available)

    Every Google BigQuery call from Hermes passes through Runlayer, where your policies can allow, alert, mask, or block it.

  • Audit trail (available)

    Each call is recorded with the user, Hermes 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.

  • Stop a call before it runs (available)

    Runlayer can deny a tool call before Hermes runs it.

  • Block output after it runs (available)

    Runlayer can block a tool’s output in Hermes and show a message in its place.

  • Redact output in place (not available)

    Hermes cannot take masked output, so Runlayer can block a tool’s output but not mask it. The gateway still applies policy to the call.

In Hermes

  • Hermes can replace blocked tool output with a message, but its after-call event is for monitoring only.

Frequently asked questions

Connect more

Find another combination