Bigquery MCP Server

@PaddyAlton

代码仓库

基本信息

分类

数据库

许可证

MIT

传输方式

stdio

作者

PaddyAlton

关于 Bigquery MCP Server

An MCP server to help AI Agents inspect the contents of a BigQuery warehouse

#bigquery #mcp #ai-agents

Bigquery MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "bigquery-mcp": {
      "command": "uv",
      "args": [
        "run",
        "--with",
        "mcp",
        "--directory",
        "/path/to/bigquery-mcp",
        "mcp",
        "run",
        "/path/to/bigquery-mcp/src/server.py"
      ],
      "env": {
        "GOOGLE_APPLICATION_CREDENTIALS": ""
      }
    }
  }
}

Bigquery MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is bigquery-mcp?

bigquery-mcp is a Model Context Protocol (MCP) server that provides AI agents with tools to examine the contents of a BigQuery data warehouse—including datasets, tables, columns, and query history. It is designed for developers using AI-powered coding tools (e.g., Cursor) to improve the quality of SQL queries by giving the agent context about the database schema and data.

How to use bigquery-mcp?

After ensuring uv is installed and a BigQuery client is available (via gcloud or a service account key set in GOOGLE_APPLICATION_CREDENTIALS), clone the repository and run uv sync. Then, in Cursor settings under MCP Servers, start a server with the command: uv run --with mcp --directory /path/to/bigquery-mcp mcp run /path/to/bigquery-mcp/src/server.py. A contextual rule file (.cursor/rules/tool-use-rule.mdc) is recommended to give the Cursor Agent proper instructions for using the tools.

Key features of bigquery-mcp

Provides AI agents with tools to list BigQuery datasets, tables, and columns.
Lets agents inspect query history for context.
Helps agents write better SQL by exposing database contents.
Easy integration with Cursor IDE via a single command.
Relies on uv for dependency management and BigQuery client library for authentication.

Use cases of bigquery-mcp

An AI coding agent needs to write a query but lacks schema awareness; it uses bigquery-mcp to list all tables and their columns first.
Exploring a new BigQuery project: an agent can fetch dataset and table names before generating analysis queries.
Reviewing past query patterns by inspecting BigQuery’s query history through the MCP tools.

常见问题

What prerequisites are required to run bigquery-mcp?

You need `uv` installed (e.g., via `brew install uv`) and a BigQuery client that can transparently create a client—usually from having `gcloud` installed locally. Alternatively, set the `GOOGLE_APPLICATION_CREDENTIALS` environment variable to point to a service account key.

How do I start bigquery-mcp in Cursor?

In Cursor settings, go to MCP Servers and add a new server with the command: `uv run --with mcp --directory /path/to/bigquery-mcp mcp run /path/to/bigquery-mcp/src/server.py`.

What tools does bigquery-mcp give to an AI agent?

The server provides tools to examine BigQuery datasets, tables, columns, and query history, giving the agent the context it needs to write better SQL queries.

What are the development dependencies?

For development you also need `Taskfile` installed (e.g., `brew install go-task`). The project uses a Taskfile for task automation.

Does bigquery-mcp assume any particular authentication method?

It currently assumes you can transparently create a BigQuery `Client`. This works when `gcloud` is installed locally—in other environments you can provide a service account key via the `GOOGLE_APPLICATION_CREDENTIALS` environment variable.

数据库分类下的更多 MCP 服务器

golfdata.online - Verified Golf Clubs

golfdata.online

Verified golf club data for AI agents: holes, par, address, phone, booking links, facilities, visitor rules and green fees for golf clubs in Spain (Canary Islands and mainland), expanding across Europe. Every fact comes

MCP DB Wizard

srmadscience

Oracle MCP server with no run-sql tool: It generates tools for each of the PL/SQL procedures, tables and approved SQL you choose. The server doesn't expose a SQL prompt, and can't reveal how it's connected to Oracle.

nuzur

nuzur is a model-first database platform for MySQL and PostgreSQL. The MCP server lets any AI assistant or agent (Claude, Cursor, Gemini, or anything else that speaks MCP) design your schema, query your data, generate mi