mcpbeat Sign in

BigQuery Data Platform MCP Server

local only

BigQuery Data Platform runs on your own machine — the client starts it, so there is no endpoint to ping. 1 303 installs a week from pypi. Last commit 8 Sep 2026.

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

1 303
Installs / week
pypi · data-platform-mcp
0
Stars
0 open issues
8 Sep 2026
Last commit
0 releases in 90 days
MIT
License
Python

What the code does

We read the source, 20 h ago · rules 3dff92dd89df

Evidence

Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.

        return subprocess.call([bash, str(path), *args])
Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

        return subprocess.call([bash, str(path), *args])

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

We found things in this code

Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch BigQuery Data Platform and you get told the day something new turns up.

Three servers free · no card

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

run in your terminal
claude mcp add data-platform-mcp -- uvx data-platform-mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "data-platform-mcp": {
      "args": [
        "data-platform-mcp"
      ],
      "command": "uvx"
    }
  }
}
~/.codex/config.toml
[mcp_servers.data-platform-mcp]
command = "uvx"
args = ["data-platform-mcp"]
.cursor/mcp.json
{
  "mcpServers": {
    "data-platform-mcp": {
      "args": [
        "data-platform-mcp"
      ],
      "command": "uvx"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "data-platform-mcp": {
      "args": [
        "data-platform-mcp"
      ],
      "command": "uvx"
    }
  }
}

This one needs environment variables set before it will start: 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.). The author declared them in the registry entry; get the values from the project itself.

Alternatives to BigQuery Data Platform

same job, measured the same way
DataCharter
by datacharter

Local-first, contract-governed data explorer with read-only, PII-masked query tools for AI agents.

1 416 installs/wk local only
Dbridge MCP
by ugurcl

Query SQLite, PostgreSQL, and MySQL in plain language - read-only, with column masking and limits.

34 installs/wk local only
Onelens MCP
by astuto-ai

Query OneLens cloud-cost data in natural language: breakdowns, trends, cost centers. Read-only.

answering
1C OData MCP
by alexgrebeshok-coder

Read-only MCP server for 1C:Enterprise via OData with metadata and query builder tools.

35 installs/wk local only
C
INFO-Subscription
by info-subscription

Exposes tools for querying subscriptions and billing data from the INFO-Subscription platform

answering
Robotbase MCP
by wygogogo19

Read-only BTC/XMR/ZEC/DOGE/LTC chain data for AI agents (16 tools)

15 tools answering
I
Glint Model Hub — image generation for AI agents
by zzzjy765

Generate and edit images with every image model on the platform. Returns the image to the agent.

local only
GCP Platform Engineer
by debilla

Read-only GCP tools for debugging incidents and finding cost savings

562 installs/wk local only

BigQuery Data Platform — questions

Answers built from our own checks of this server.

Why is there no uptime for BigQuery Data Platform?
BigQuery Data Platform runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package data-platform-mcp was installed 1 303 times last week.
How do I connect BigQuery Data Platform?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls data-platform-mcp straight from pypi; nothing to host, nothing to sign up for.
How many people use BigQuery Data Platform?
The pypi package data-platform-mcp was installed 1 303 times in the last week. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is BigQuery Data Platform open source?
Yes — it is published under the MIT licence, written in Python and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.