# Google BigQuery

The Google BigQuery MCP server connects an agent to BigQuery for dataset discovery, schema checks, and read-only SQL queries.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · 6986 installs
- Author: bigquery
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://smithery.ai/server/bigquery
- Updated: 2026-03-27
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/google-bigquery

## What it does

The server gives an agent access to BigQuery resources in a Google Cloud project. It can return dataset and table IDs, fetch metadata for either resource, and send a SQL query for its result. These actions are exposed through `list_dataset_ids`, `get_dataset_info`, `list_table_ids`, `get_table_info`, and `execute_sql`.

The connection uses the HTTP endpoint `https://bigquery.run.tools`. Queries are limited to `SELECT`; `INSERT`, `UPDATE`, `DELETE`, and stored procedures are rejected. That means this MCP server cannot write changes to BigQuery.

## Requirements
- Remote server: `https://bigquery.run.tools`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http bigquery https://bigquery.run.tools
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add google-bigquery --url https://bigquery.run.tools
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "google-bigquery": {
            "url": "https://bigquery.run.tools"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "google-bigquery": {
            "type": "http",
            "url": "https://bigquery.run.tools"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http google-bigquery https://bigquery.run.tools
```

## When to use it
- find datasets in a Google Cloud project
- list tables inside a BigQuery dataset
- inspect table or dataset metadata
- run a read-only SQL query

## Example prompts
- List the dataset IDs in my Google Cloud project.
- Inspect the schema for the `orders` table in the `analytics` dataset.
- Run a `SELECT` query on the `events` table and return the results.

## Similar
- [bigquery-ai-ml](https://affpapa.org/en/nevibecode/skills/bigquery-ai-ml.md) — skill · 7033 installs
- [bigquery-udfs](https://affpapa.org/en/nevibecode/skills/bigquery-udfs.md) — skill · 81 installs
- [bigquery-mcp](https://affpapa.org/en/nevibecode/mcp/bigquery-mcp.md) — MCP server · ★ 10 repo stars
- [bigquery-data-analytics](https://affpapa.org/en/nevibecode/plugins/bigquery-data-analytics.md) — plugin · ★ 53 repo stars
- [bigquery-agent-analytics-sdk](https://affpapa.org/en/nevibecode/skills/bigquery-agent-analytics-sdk.md) — skill · 773 installs
- [google-cloud-data-engineering-hub](https://affpapa.org/en/nevibecode/skills/google-cloud-data-engineering-hub.md) — skill · 1100 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
