# MCP BigQuery Server (MCP server)

> MCP BigQuery Server is an MCP server that provides secure, read-only access to BigQuery datasets. It has 148 GitHub stars, is released under the MIT license and runs locally with npx -y @ergut/mcp-bigquery-server. It works with Claude Desktop, Claude Code, Cursor and VS Code.

This is a server that lets your LLMs (like Claude) talk directly to your BigQuery data — read-only, with no ability to mutate your warehouse. Think of it as a friendly translator that sits between your AI assistant and your database, making sure they can chat securely and efficiently.

## Key facts

| Fact | Value |
|---|---|
| Repository | https://github.com/ergut/mcp-bigquery-server |
| GitHub stars | 148 |
| License | MIT |
| Language | TypeScript |
| Transport | stdio |
| Packages | npm: @ergut/mcp-bigquery-server |
| Remote URL | none |
| Needs API key | no |
| Official | no |
| Works with | Claude Desktop, Claude Code, Cursor, VS Code |
| Category | Data & analytics |
| Latest release | v1.0.3 (Apr 3, 2025) |
| Last commit | May 22, 2026 |

## Install

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "mcp-bigquery-server": {
      "command": "npx",
      "args": [
        "-y",
        "@ergut/mcp-bigquery-server"
      ]
    }
  }
}
```

Settings > Developer > Edit Config. macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\. Restart Claude Desktop afterwards.

### Claude Code

```sh
claude mcp add --transport stdio mcp-bigquery-server -- npx -y @ergut/mcp-bigquery-server
```

### Cursor (.cursor/mcp.json)

```json
{
  "mcpServers": {
    "mcp-bigquery-server": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@ergut/mcp-bigquery-server"
      ]
    }
  }
}
```

Project file; use ~/.cursor/mcp.json to enable it in every project.

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "mcp-bigquery-server": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@ergut/mcp-bigquery-server"
      ]
    }
  }
}
```

Config formats checked against the official docs on 2026-10-07.

## Similar MCP servers

- [Betterlytics](https://appsgit.com/mcp-servers/betterlytics): Query your Betterlytics web analytics from AI agents: traffic, funnels, journeys, errors, uptime. (180 stars, AGPL-3.0, official, needs API key)
- [Everyrow MCP Server](https://appsgit.com/mcp-servers/everyrow-mcp-server): Give your AI a research team. Forecast, score, classify, or research every row of a dataset. (57 stars, MIT, official, needs API key)
- [Muxinc MCP Server](https://appsgit.com/mcp-servers/muxinc-mcp-server): The official MCP Server for the Mux API. (182 stars, Apache-2.0, official, needs API key)
- [Markifact - Ads & Analytics](https://appsgit.com/mcp-servers/markifact-ads-analytics): AI marketing agent for Google Ads, Meta, GA4, TikTok, LinkedIn, Shopify, HubSpot and more. (54 stars, MIT, official)
- [Google Analytics MCP](https://appsgit.com/mcp-servers/google-analytics-mcp): GA4 MCP server for AI agents: schema discovery, server-side aggregation, analysis-ready defaults. (243 stars, MIT, needs API key)
- [Spytrend](https://appsgit.com/mcp-servers/spytrend): Analytics, advertising: Facebook/Meta, TikTok, competitor ads. (34 stars, MIT, official)

---

Canonical page: https://appsgit.com/mcp-servers/mcp-bigquery-server
Source: appsgit (https://appsgit.com), the app store for github. Data from the GitHub API, refreshed daily.
Machine access: JSON API https://appsgit.com/api/v1/apps (OpenAPI: https://appsgit.com/openapi.json), MCP server https://mcp.appsgit.com/mcp, full index https://appsgit.com/llms-full.txt.