# bigquery-mcp

This MCP server lets AI agents inspect Google BigQuery schemas, list tables, and run SQL queries when direct data access is needed.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 10
- Author: SnowLeopard-AI
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/SnowLeopard-AI/bigquery-mcp
- Updated: 2026-03-27
- HTML: https://affpapa.org/en/nevibecode/mcp/bigquery-mcp

## What it does

bigquery-mcp connects an AI agent to Google BigQuery through MCP. It exposes resources for available tables and individual table schemas, while the `query` tool runs BigQuery SQL and returns the result. The `list_tables` and `get_schema` tools can be enabled as configuration options.

You need a Google Cloud Project with BigQuery enabled and permission to submit jobs, plus `gcloud` and `uv`. Authenticate the local environment with `gcloud auth application-default login`, then run the server through `uvx sl-bigquery-mcp`. Queries will fail without a project that can submit BigQuery jobs.

For Claude Code, add the server with `claude mcp add bigquery-mcp -- uvx sl-bigquery-mcp`. Codex and Gemini CLI have their own add commands; Cursor and GitHub Copilot use MCP configuration entries that start `uvx`.

## Requirements
- Needs: Python and uv (commands run via uvx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add bigquery-mcp -- uvx sl-bigquery-mcp
```
uvx runs the command named after the package; if the README names another one, use uvx --from sl-bigquery-mcp <command>

### Codex

**Platform CLI**
```bash
codex mcp add bigquery-mcp -- uvx sl-bigquery-mcp
```
uvx runs the command named after the package; if the README names another one, use uvx --from sl-bigquery-mcp <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "bigquery-mcp": {
            "command": "uvx",
            "args": [
                "sl-bigquery-mcp"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from sl-bigquery-mcp <command>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "bigquery-mcp": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "sl-bigquery-mcp"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from sl-bigquery-mcp <command>

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add bigquery-mcp uvx sl-bigquery-mcp
```
uvx runs the command named after the package; if the README names another one, use uvx --from sl-bigquery-mcp <command>

## When to use it
- list available BigQuery tables
- inspect a table schema
- run SQL against BigQuery data
- answer data questions through an AI agent

## Example prompts
- List the tables available in the connected BigQuery dataset.
- Inspect the schema of `project.dataset.table` and explain its fields.
- Run a SQL query against the data and return the results with a short explanation.

## Similar
- [bigquery-udfs](https://affpapa.org/en/nevibecode/skills/bigquery-udfs.md) — skill · 81 installs
- [bigquery-basics](https://affpapa.org/en/nevibecode/skills/bigquery-basics.md) — skill · 17678 installs
- [bigquery-agent-analytics-sdk](https://affpapa.org/en/nevibecode/skills/bigquery-agent-analytics-sdk.md) — skill · 768 installs
- [ga4-bigquery-schema](https://affpapa.org/en/nevibecode/skills/ga4-bigquery-schema.md) — skill · ★ 111
- [bigquery-pipeline-audit](https://affpapa.org/en/nevibecode/skills/bigquery-pipeline-audit.md) — skill · 8800 installs
- [looker-studio-bigquery](https://affpapa.org/en/nevibecode/skills/looker-studio-bigquery.md) — skill · 389 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