BigQuery Data Platform MCP Server

by debillaio.github.deBilla/data-platform-mcpv0.4.0

Read-only BigQuery tools for plain-language data questions, with a cost gate on every query

0Pythonstdioofficial registry

context tax

queued

security

queued

cold start

queued

freshness

Active18d ago

Install BigQuery Data Platform MCP server

claude mcp add data-platform -- uvx data-platform-mcp

{
  "mcpServers": {
    "data-platform": {
      "command": "uvx",
      "args": [
        "data-platform-mcp"
      ]
    }
  }
}

Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project).

{
  "mcpServers": {
    "data-platform": {
      "command": "uvx",
      "args": [
        "data-platform-mcp"
      ]
    }
  }
}

Settings → Developer → Edit Config (claude_desktop_config.json), then restart.

{
  "servers": {
    "data-platform": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "data-platform-mcp"
      ]
    }
  }
}

Add to .vscode/mcp.json in your workspace.

{
  "mcpServers": {
    "data-platform": {
      "command": "uvx",
      "args": [
        "data-platform-mcp"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json.

Configuration

Variable	Required	Secret	Description
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 ~/.config/data-platform-mcp/config.toml.
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 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.
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.