mcp bigquery dryrun
这 mcp-bugquery-dryrun 该包为BigQuery SQL验证和模拟运行分析提供了一个最小的MCP服务器。该服务器提供了两种工具，用于验证和分析BigQuery SQL查询，而无需执行它们。
\*\*重要提示：此服务器不执行查询。所有操作仅为模拟运行。成本估算是基于处理字节的近似值\*\*
特性
- SQL验证：在不运行查询的情况下检查BigQuery SQL语法
- 干运行分析：获取成本估算、参考表和架构预览
- 参数支持：验证参数化查询
- 成本估算：根据处理的字节数计算美元估算值
快速开始
先决条件
- Python 3.10+
- 启用BigQuery API的Google云SDK
- 已配置应用程序默认凭据
安装
来自PyPI（推荐）
# Install from PyPI
pip install mcp-bigquery-dryrun
# Or with uv
uv pip install mcp-bigquery-dryrun来源
# Clone the repository
git clone https://github.com/caron14/mcp-bigquery-dryrun.git
cd mcp-bigquery-dryrun
# Install with uv (recommended)
uv pip install -e .
# Or install with pip
pip install -e .认证
设置应用程序默认凭据：
gcloud auth application-default login或者使用服务帐户密钥：
export GOOGLE_APPLICATION_CREDENTIALS=/path/to/service-account-key.json配置
环境变量
| 变量 | 描述 | 默认值 |
|---|---|---|
BQ_PROJECT | GCP项目ID | 来自ADC |
BQ_LOCATION | BigQuery位置（例如，美国、欧盟、亚洲东北1） | 无 |
SAFE_PRICE_PER_TIB | 成本估算的每TiB默认价格 | 5.0 |
Claude代码集成
添加到您的Claude代码配置中：
{
"mcpServers": {
"bq-dryrun": {
"command": "mcp-bigquery-dryrun",
"env": {
"BQ_PROJECT": "your-gcp-project",
"BQ_LOCATION": "asia-northeast1",
"SAFE_PRICE_PER_TIB": "5.0"
}
}
}
}或者，如果从源代码安装：
{
"mcpServers": {
"bq-dryrun": {
"command": "python",
"args": ["-m", "mcp_bigquery_dryrun"],
"env": {
"BQ_PROJECT": "your-gcp-project",
"BQ_LOCATION": "asia-northeast1",
"SAFE_PRICE_PER_TIB": "5.0"
}
}
}
}工具
bq_validate_sql
在不执行查询的情况下验证BigQuery SQL语法。
输入：
{
"sql": "SELECT * FROM dataset.table WHERE id = @id",
"params": {"id": "123"} // Optional
}成功响应：
{
"isValid": true
}错误响应：
{
"isValid": false,
"error": {
"code": "INVALID_SQL",
"message": "Syntax error at [3:15]",
"location": {
"line": 3,
"column": 15
},
"details": [...] // Optional
}
}bq_dry_run_sql
执行模拟运行以获取成本估算和元数据，而无需执行查询。
输入：
{
"sql": "SELECT * FROM dataset.table",
"params": {"id": "123"}, // Optional
"pricePerTiB": 6.0 // Optional, overrides default
}成功响应：
{
"totalBytesProcessed": 1073741824,
"usdEstimate": 0.005,
"referencedTables": [
{
"project": "my-project",
"dataset": "my_dataset",
"table": "my_table"
}
],
"schemaPreview": [
{
"name": "id",
"type": "STRING",
"mode": "NULLABLE"
},
{
"name": "created_at",
"type": "TIMESTAMP",
"mode": "REQUIRED"
}
]
}错误响应：
{
"error": {
"code": "INVALID_SQL",
"message": "Table not found: dataset.table",
"details": [...] // Optional
}
}例子
验证简单查询
# Tool: bq_validate_sql
{
"sql": "SELECT 1"
}
# Returns: {"isValid": true}使用参数进行验证
# Tool: bq_validate_sql
{
"sql": "SELECT * FROM users WHERE name = @name AND age > @age",
"params": {
"name": "Alice",
"age": 25
}
}获取成本估算
# Tool: bq_dry_run_sql
{
"sql": "SELECT * FROM `bigquery-public-data.samples.shakespeare`",
"pricePerTiB": 5.0
}
# Returns bytes processed, USD estimate, and schema分析复杂查询
# Tool: bq_dry_run_sql
{
"sql": """
WITH user_stats AS (
SELECT user_id, COUNT(*) as order_count
FROM orders
GROUP BY user_id
)
SELECT * FROM user_stats WHERE order_count > 10
"""
}测试
使用pytest运行测试：
# Run all tests (requires BigQuery credentials)
pytest tests/
# Run only tests that don't require credentials
pytest tests/test_min.py::TestWithoutCredentials发展
# Install development dependencies
uv pip install -e ".[dev]"
# Run the server locally
python -m mcp_bigquery_dryrun
# Or using the console script
mcp-bigquery-dryrun局限性
- 无查询执行：此服务器仅执行模拟运行和验证
- 成本估算：美元估计值是基于处理字节的近似值
- 参数类型：初始实现将所有参数视为STRING类型
- 缓存已禁用：查询始终使用
use_query_cache=False为了获得准确的估计
许可证
阿帕奇-2.0
更新日志
0.1.0 (2024-08-12)
- 初始版本