BigQuery Data Platform
Read-only BigQuery tools for plain-language data questions, with a cost gate on every query
Open the source (opens github.com) https://github.com/debilla/bigquery-mcp
Before you use it
- Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
What it is
MCP servers from io.github.deBilla.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
pypi package (stdio)
data-platform-mcp@0.4.0
From the server's entry in the official MCP Registry
Settings it asks for
BQ_MCP_ENVIRONMENTS· JSON map of environment name to BigQuery settings (project, location, impersonate, dataset_allowlist, byte caps). Omit when using a config file at…BQ_MCP_DEFAULT_ENVIRONMENT· Environment used when a tool call omits the environment argument.BQ_MCP_CONFIG· Path to a TOML config file, overriding ~/.config/data-platform-mcp/config.toml.BQ_IMPERSONATE_SERVICE_ACCOUNT· 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`.BQ_PROJECT· GCP project whose BigQuery datasets are queried. Falls back to the project associated with Application Default Credentials.BQ_LOCATION· BigQuery location for jobs and datasets. Defaults to US.BQ_CODE_ASSET_LOCATION· Region holding BigQuery Studio notebooks and saved queries. Separate from BQ_LOCATION and usually different: code assets are regional and Dataform rejects…BQ_DATASET_ALLOWLIST· Comma-separated dataset IDs the server may read. Empty means all datasets.BQ_WARN_BYTES· Scan size above which a query is returned for user confirmation instead of run. Defaults to 1 GiB.BQ_MAX_BYTES_BILLED· Hard per-query scan cap; a query estimated above this never runs. Defaults to 5 GiB.BQ_MCP_AUDIT_LOG· Path for the JSONL tool-call audit log, or 'off' to disable it. SQL text is never recorded, only a hash and a length.
Related
-
Apify MCP server
MCP serversLets an agent run Apify's ready-made scrapers to pull data from websites, search engines, maps and social platforms.
-
bigquery-mcp
MCP serversA SnowLeopardAI-managed MCP server that provides access to Google BigQuery data.
sl-bigquery-mcp@0.1.9 -
dataops-testgen
MCP serversOpen-source data quality tool: profiles tables, generates data quality tests from the profiling results, and runs them on a schedule with freshness, volume, and schema monitoring. Web UI, REST API, and MCP server. 14 databases plus CSV, Parquet, and JSON files. Apache 2.0.
git clone https://github.com/DataKitchen/dataops-testgen.git -
Camber - Remote Agentic Data Science
MCP serversRemote data science agents for Snowflake, Databricks & BigQuery in Claude/Cursor via MCP
-
orionbelt-semantic-layer
MCP serversSource-available semantic and context layer, rule engine, and semantic sidecar for agentic AI and governed analytics. Compiles declarative YAML models into optimized SQL, KPIs, and semantic context across 8 SQL dialects.
git clone https://github.com/ralforion/orionbelt-semantic-layer.git -
patents-mcp-server
MCP serversPatent intelligence — USPTO Open Data, PTAB, EPO OPS and BigQuery full-text search.
patents-mcp-server@1.2.3