加载中…
Read-only BigQuery tools for plain-language data questions, with a cost gate on every query
BigQuery Data Platform 是 ChatHome Skills 收录的 MCP 条目,来源为 Official MCP Registry,质量分 73/100。 作为 Model Context Protocol 服务器,它向 Claude、Cursor、Copilot 等兼容 MCP 的 LLM 客户端暴露可直接调用的工具,让 agent 的能力超出模型内置范围。 该条目由 ChatHome Skills 的每日抓取从官方 registry 和 GitHub 发现查询中收录,每次运行都会重新核验仓库事实、新鲜度信号和安装元数据。 质量分综合了官方 registry 收录情况、可用安装命令、许可证完整性、仓库活跃度和 GitHub star 趋势,完整算法说明见来源页。安装命令已列于上方,可直接复制使用。 在将 BigQuery Data Platform 加入生产 agent 工作流前,请核对上方的最近更新日期和仓库状态——下方事实快照是最近一次抓取的时点值。
uvx data-platform-mcp==0.4.0运行此命令前,请先核对上游源码。
{
"_meta": {
"io.modelcontextprotocol.registry/official": {
"status": "active",
"isLatest": true,
"updatedAt": "2026-09-22T02:42:16.465908Z",
"publishedAt": "2026-09-22T02:42:16.465908Z",
"statusChangedAt": "2026-09-22T02:42:16.465908Z"
}
},
"server": {
"name": "io.github.deBilla/data-platform-mcp",
"title": "BigQuery Data Platform",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"version": "0.4.0",
"packages": [
{
"version": "0.4.0",
"transport": {
"type": "stdio"
},
"identifier": "data-platform-mcp",
"registryType": "pypi",
"environmentVariables": [
{
"name": "BQ_MCP_ENVIRONMENTS",
"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_DEFAULT_ENVIRONMENT",
"description": "Environment used when a tool call omits the environment argument."
},
{
"name": "BQ_MCP_CONFIG",
"description": "Path to a TOML config file, overriding ~/.config/data-platform-mcp/config.toml."
},
{
"name": "BQ_IMPERSONATE_SERVICE_ACCOUNT",
"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_PROJECT",
"description": "GCP project whose BigQuery datasets are queried. Falls back to the project associated with Application Default Credentials."
},
{
"name": "BQ_LOCATION",
"description": "BigQuery location for jobs and datasets. Defaults to US."
},
{
"name": "BQ_CODE_ASSET_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_DATASET_ALLOWLIST",
"description": "Comma-separated dataset IDs the server may read. Empty means all datasets."
},
{
"name": "BQ_WARN_BYTES",
"description": "Scan size above which a query is returned for user confirmation instead of run. Defaults to 1 GiB."
},
{
"name": "BQ_MAX_BYTES_BILLED",
"description": "Hard per-query scan cap; a query estimated above this never runs. Defaults to 5 GiB."
},
{
"name": "BQ_MCP_AUDIT_LOG",
"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."
}
]
}
],
"repository": {
"url": "https://github.com/deBilla/bigquery-mcp",
"source": "github"
},
"websiteUrl": "https://debilla.github.io/bigquery-mcp/",
"description": "Read-only BigQuery tools for plain-language data questions, with a cost gate on every query"
}
}