BigQuery Data Platform

io.github.deBilla/data-platform-mcpv0.1.2Databases

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

The current version, v0.1.2, was published to the official MCP registry on 2026-09-02. It is distributed as data-platform-mcp on PyPI, filed under Databases by this index, and declares 10 environment variables. Removals and unreachable sources are measured across every server this index tracks, contract drift across the servers that answer in consecutive snapshots; the index's current counts put this record in context.

In-path gate · all MCP tools

Using BigQuery Data Platform in Claude, Cursor, Gemini CLI, Cline, or Zed?

MCP tool contracts can change remotely with no version bump. The mcpindex gate pins each contract and HOLDs the call when it drifts-before your agent acts. Zero credentials. This is not the package install for this server itself (use Install this server for that).

Install the mcpindex gate (one command)

Rewrites your MCP host config so each server launches behind the gate. Inspect first: curl -fsSL https://mcpindex.ai/install.sh | less

uv tool install mcpindex-gate && mcpindex-config-wire

Auditable install path →Watch it hold a drift →

Trust verdict · v1 advisory · method

NOT YET SCREENEDno verdict on file

Verdict not yet evaluated for this tool. The semantic screen takes adversarial cases first; coverage rolls out as the corpus expands (15/150 labels to graduation). The deterministic conformance probe is built but has not yet run on the public corpus, so a recorded verdict here is REVIEW or UNVERIFIED, never a clearing ALLOW. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: the eval, four-state verdict, honest limits.

Own this server? Screen its description →

That verdict was true at screening time (snapshot 2026-09-02).

Contracts can change after screening, with no version bump. The gate pins BigQuery Data Platform’s tool contracts on first sight and holds any silent change before your agent acts - the check that keeps being true on Tuesday.

See your first HOLD in 2 minutes →

Environment variables

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_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.

MCP quality score · maturity, not trust · methodology

freshness

completeness

installability

documentation

stability

Alternatives in Databases

Cortex RMCP

ai.dinglebear/cortex

Self-hosted homelab log intelligence over MCP, CLI, and REST with SQLite/FTS.

Aiven MCP

io.aiven/mcp

Provision PostgreSQL, manage Apache Kafka, and deploy apps with Aiven - all from your AI assistant.

Agent Swarm

io.github.desplega-ai/agent-swarm

Full Agent Swarm API and MCP server with local SQLite storage for multi-agent orchestration.

Install this server

Claude Desktop (uvx)

{
  "mcpServers": {
    "data-platform-mcp": {
      "command": "uvx",
      "args": [
        "--",
        "data-platform-mcp"
      ],
      "env": {
        "BQ_MCP_ENVIRONMENTS": "<bq_mcp_environments>",
        "BQ_MCP_DEFAULT_ENVIRONMENT": "<bq_mcp_default_environment>",
        "BQ_MCP_CONFIG": "<bq_mcp_config>",
        "BQ_IMPERSONATE_SERVICE_ACCOUNT": "<bq_impersonate_service_account>",
        "BQ_PROJECT": "<bq_project>",
        "BQ_LOCATION": "<bq_location>",
        "BQ_DATASET_ALLOWLIST": "<bq_dataset_allowlist>",
        "BQ_WARN_BYTES": "<bq_warn_bytes>",
        "BQ_MAX_BYTES_BILLED": "<bq_max_bytes_billed>",
        "BQ_MCP_AUDIT_LOG": "<bq_mcp_audit_log>"
      }
    }
  }
}

Verdict API

curl -s mcpindex.ai/api/v1/trust/server/io-github-debilla-data-platform-mcp

Free-tier verdict as JSON: decision + dimensions + severity. Call it from your agent before it invokes a tool it just discovered.

Details

version: v0.1.2
category: Databases
quality: 85 / 100
operator: deBilla

Listing

Listed from the official MCP registry. Unclaimed by its maintainer. Maintainer? Email us →

Provenance

Each verdict is bound to a hash of the exact description it judged, so a re-crawl that changes the text produces a new record rather than silently inheriting this one. Verdict history is hash-chained and anchored to Bitcoin via OpenTimestamps (latest confirmed at block 965,121). Verify it yourself.

Links

Repository →