How to Connect BigQuery to an AI Agent
Auth setup
1. Enable BigQuery API in Cloud Console. 2. Create service account with BigQuery roles. 3. Download JSON key file. 4. Or use Application Default Credentials.
Key facts
| Base URL | https://bigquery.googleapis.com/bigquery/v2/ |
|---|
| API version | v2 |
|---|
| Auth | OAuth 2.0 or service account. Enable BigQuery API in Google Cloud Console. |
|---|
| Token URL | https://oauth2.googleapis.com/token |
|---|
| Scopes | https://www.googleapis.com/auth/bigquery |
|---|
| Request body | application/json |
|---|
| Pagination | token-based: pageToken in response. Use in next request. |
|---|
| Rate limit | Concurrent queries: 100 per project. API: 100 req/sec. |
|---|
| Error format | JSON: {"error":{"code":403,"message":"...","errors":[...]}} |
|---|
Key endpoints
| Method | Path | Description |
|---|
POST | /projects/{projectId}/queries | Run SQL query |
GET | /projects/{projectId}/datasets | List datasets |
POST | /projects/{projectId}/jobs | Create job (load, query, extract) |
Quickstart
POST /bigquery/v2/projects/{projectId}/queries
Authorization: Bearer {access_token}
{"query":"SELECT * FROM `project.dataset.table` LIMIT 10","useLegacySql":false}
Agent pitfalls & tips
- Free tier: 1TB query processing/month, 10GB storage.
- Always set useLegacySql:false for standard SQL.
- Use client libraries (@google-cloud/bigquery) over raw REST.
- Table names use backtick syntax: `project.dataset.table`.
- Dry run: set dryRun:true to estimate query cost without running.
Source: curated by KanseiLink from official documentation (docs) and registry checks. Last reviewed: 2026-04-07. Specs change — verify against the official docs before production use.
Frequently Asked Questions
What is BigQuery's AEO score?
▼
BigQuery has an AEO score of 0.90 and is rated AA (Strong agent support with minor gaps). AEO (Agent Engine Optimization) measures how well a SaaS service works with AI agents. Scores range from 0.00 to 1.00, with grades from AAA (best) to D (not agent-ready).
Is BigQuery AI-agent-ready?
▼
BigQuery is currently connectable for AI agent use. Third-party MCP integrations are available for this service. For detailed connection guides, auth setup, and known pitfalls, use the KanseiLink MCP tool.
How does BigQuery compare to other BI & Analytics services?
▼
In the BI & Analytics category, BigQuery is rated AA. KanseiLink evaluates services based on MCP availability, API quality, documentation, auth-guide clarity, and integration recipe availability (methodology published). Visit the full rankings at kansei-link.com to see how BigQuery compares.
How can I integrate BigQuery with an AI agent?
▼
The fastest way to integrate BigQuery with an AI agent is through KanseiLink MCP. Install it with: npx @kansei-link/mcp-server — then use the search_services and get_service_detail tools to get the current auth setup, endpoints, rate limits, and agent-specific tips. This data is kept fresh from registry checks, curated official-doc guides, and agent reports.
How do I authenticate with BigQuery?
▼
OAuth 2.0 or service account. Enable BigQuery API in Google Cloud Console. Setup: 1. Enable BigQuery API in Cloud Console. 2. Create service account with BigQuery roles. 3. Download JSON key file. 4. Or use Application Default Credentials.
What are BigQuery's API rate limits?
▼
Concurrent queries: 100 per project. API: 100 req/sec.