MCP低风险未认领
BigQuery Data Platform
Read-only BigQuery tools for plain-language data questions, with a cost gate on every query
deBilladebilla/data-platform-mcp
server.json
{
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"name": "io.github.deBilla/data-platform-mcp",
"description": "Read-only BigQuery tools for plain-language data questions, with a cost gate on every query",
"title": "BigQuery Data Platform",
"repository": {
"url": "https://github.com/deBilla/bigquery-mcp",
"source": "github"
},
"version": "0.4.0",
"websiteUrl": "https://debilla.github.io/bigquery-mcp/",
"packages": [
{
"registryType": "pypi",
"identifier": "data-platform-mcp",
"version": "0.4.0",
"transport": {
"type": "stdio"
},
"environmentVariables": [
{
"description": "JSON map of environment name to BigQuery settings (project, location, impersonate, dataset_allowlist, byte caps). Omit when using a config file at ~/.config/data-platform-mcp/config.toml.",
"name": "BQ_MCP_ENVIRONMENTS"
},
{
"description": "Environment used when a tool call omits the environment argument.",
"name": "BQ_MCP_DEFAULT_ENVIRONMENT"
},
{
"description": "Path to a TOML config file, overriding ~/.config/data-platform-mcp/config.toml.",
"name": "BQ_MCP_CONFIG"
},
{
"description": "Read-only service account to impersonate, making read-only a property of the identity rather than of this code. Create it with `data-platform-mcp setup`.",
"name": "BQ_IMPERSONATE_SERVICE_ACCOUNT"
},
{
"description": "GCP project whose BigQuery datasets are queried. Falls back to the project associated with Application Default Credentials.",
"name": "BQ_PROJECT"
},
{
"description": "BigQuery location for jobs and datasets. Defaults to US.",
"name": "BQ_LOCATION"
},
{
"description": "Region holding BigQuery Studio notebooks and saved queries. Separate from BQ_LOCATION and usually different: code assets are regional and Dataform rejects multi-regions, so datasets in US typically pair with code assets in a region like us-central1. A wrong region returns an empty list rather than an error. Defaults to BQ_LOCATION.",
"name": "BQ_CODE_ASSET_LOCATION"
},
{
"description": "Comma-separated dataset IDs the server may read. Empty means all datasets.",
"name": "BQ_DATASET_ALLOWLIST"
},
{
"description": "Scan size above which a query is returned for user confirmation instead of run. Defaults to 1 GiB.",
"name": "BQ_WARN_BYTES"
},
{
"description": "Hard per-query scan cap; a query estimated above this never runs. Defaults to 5 GiB.",
"name": "BQ_MAX_BYTES_BILLED"
},
{
"description": "Path for the JSONL tool-call audit log, or 'off' to disable it. SQL text is never recorded, only a hash and a length.",
"name": "BQ_MCP_AUDIT_LOG"
}
]
}
]
}权限
声明检测
运行代码—
python安装—
pypi:data-platform-mcp@0.4.0安装时运行脚本—无
网络无无
需要的凭据无无
工作区外的路径—无
智能体工具—无
检查
低风险 · 没有发现需要提醒的地方。
未经人工审核 · 已做规则检查;模型审核尚未开启。
版本
- #10.4.0最新2026年10月7日
BigQuery Data Platform在 Codeg 中打开