From Harness Data
Google BigQuery remote MCP conventions (preview) — GCP Workload Identity Federation auth never a static service-account key, a read-only bigquery.jobUser + dataViewer role, mandatory partition pruning, and in-place query streaming. Use when querying BigQuery, wiring the BigQuery MCP, or setting up read-only warehouse access on GCP.
How this skill is triggered — by the user, by Claude, or both
Slash command
/harness-data:addon-bigquery-mcpThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
- **Preview status (Jan 2026)** — re-verify GA status each quarter.
BIGQUERY_SERVICE_ACCOUNT_KEY_JSON is refused by the
block-static-warehouse-creds.sh shared hook.bigquery.jobUser + bigquery.dataViewer. No bigquery.dataEditor.block-unbounded-sql.sh
(no WHERE) and also waste cost; review every plan.This addon's BigQuery MCP carries a secret OAuth token, so it is not
auto-started by the plugin. Add it to your project's .mcp.json only when
you want governed BigQuery access, then set BIGQUERY_OAUTH_TOKEN in your
environment (mint it via Workload Identity Federation — never a static
service-account key):
{
"mcpServers": {
"bigquery": {
"type": "http",
"url": "https://bigquery.googleapis.com/mcp",
"headers": { "Authorization": "Bearer ${BIGQUERY_OAUTH_TOKEN}" }
}
}
}
npx claudepluginhub camilool8/harness-engineering-templates --plugin harness-dataProvides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Searches MemPalace before answering questions about past work, people, projects, or prior decisions. Returns verbatim stored content instead of guessing from model memory.