VendorGoogle
Connects overhttp

Our grade: 4 checks

Login Login required, broad access
Upkeep Active · 2026-10
Known bugs 0 open
Connection http

Based on public data, not a full audit. See how we grade. Something changed? Request a re-grade.

Community rating

4.0 9 reviews
56% would trust it in production
  • 5 3
  • 4 4
  • 3 1
  • 2 1
  • 1 0

Trust in production

  • Trust it - 56%
  • With caveats - 33%
  • Wouldn't - 11%

78% would recommend this server

How reviewers scored it

  • Setup & docs 4.1
  • Auth experience 3.4
  • Reliability 4.0
  • Maintainer responsiveness 4.1

Why it got a B

Google's official managed server, hosted over HTTPS. It refuses API keys and uses OAuth plus IAM, queries run inside BigQuery rather than on your machine, and an execute_sql_readonly tool blocks DML, DDL and UDFs. No advisories on record. Biggest deductions: the OAuth scope covers all of BigQuery, the read-write execute_sql tool is also on unless an IAM deny policy blocks it, and the server is closed source, so maintenance is one band lower. Give the agent its own identity with only the Data Viewer and Job User roles.

How to connect

Hosted: https://bigquery.googleapis.com/mcp (on when the BigQuery API is enabled; OAuth or Google credentials, no API keys)

Is BigQuery MCP Server safe?

Is BigQuery MCP Server safe to use?

BigQuery MCP Server grades B (solid, with minor gaps). Login is required, but access is coarse: one sign-in or key covers more than your agent needs, so grant the narrowest account you can. Upkeep is hard to verify (closed source or a single maintainer), so pin the version you tested.

Does BigQuery MCP Server have known vulnerabilities?

Not in our current data: it has no open CVEs or advisories. We re-check as new ones are published.

Does BigQuery MCP Server support authentication?

Yes. It requires a login, so access can be tied to a person or a scoped key.

Embed this badge

Maintain this server? Add the grade to your README.

TrustedMCP grade B

Markdown

[![TrustedMCP grade B](https://trustedmcp.io/badge/bigquery-mcp-server.svg)](https://trustedmcp.io/servers/bigquery-mcp-server)

HTML

<a href="https://trustedmcp.io/servers/bigquery-mcp-server"><img src="https://trustedmcp.io/badge/bigquery-mcp-server.svg" alt="TrustedMCP grade B" height="80"></a>

Community reviews

Sofia Rossi CTO, early-stage startup
Trusts with caveats Recommends

Saves me a context switch every hour

Hooked BigQuery MCP Server into Claude Code and it worked on the first try. Being closed source, I cannot audit it, but the vendor has been responsive. Auth is handled properly, and revoking access later was one click. Worth it, just do not skip the hardening steps.

Used for Prototyping queries before writing code

  • Setup & docs 4/5
  • Auth experience 4/5
  • Reliability 3/5
  • Maintainer responsiveness 5/5
Anika Gupta Solo founder
Trusts in production Recommends

Surprisingly polished

Set this up for our team after comparing a few options. I like that access goes through a proper sign-in instead of a long-lived secret on disk.

Used for Generating SQL for ad-hoc reports

  • Setup & docs 5/5
  • Auth experience 4/5
  • Reliability 5/5
  • Maintainer responsiveness 4/5
Leila Ahmadi Indie hacker
Would not trust in production

Mixed feelings after two weeks

Useful tool, though I would not hand it to a junior unsupervised. The OAuth flow worked first time in Claude Code. I like that access goes through a proper sign-in instead of a long-lived secret on disk. Keeping it to local experiments for now.

Used for Debugging data issues in staging

  • Setup & docs 3/5
  • Auth experience 3/5
  • Reliability 3/5
  • Maintainer responsiveness 4/5
Zara Ali Software engineer, agency
Trusts with caveats

Fine for a demo, not for prod

It works in a demo, but things got shaky under real use. Hosted endpoint means no local process to babysit. Scoped the token to just what the agent needs and it respected that. Recommended, with sensible guardrails.

Used for Checking data quality after imports

  • Setup & docs 2/5
  • Auth experience 2/5
  • Reliability 2/5
  • Maintainer responsiveness 4/5
Amara Okeke Eng lead, fintech
Trusts in production Recommends

Worth the five minutes to set up

Our agents call this dozens of times a day. Filed an issue and got a reply within two days.

Used for Schema exploration during a migration

  • Setup & docs 5/5
  • Auth experience 4/5
  • Reliability 5/5
  • Maintainer responsiveness 5/5
Raj Malhotra Analytics engineer
Trusts in production Recommends

Better than the DIY script it replaced

Of the BigQuery integrations I tried, this one is the most predictable. Sign-in flow was painless and I never had to paste a key into a config file. I gave it a database user that can only read the tables it needs. You can tell it is actively maintained, the rough edges keep getting fixed.

Used for Read-only analytics questions

  • Setup & docs 5/5
  • Auth experience 3/5
  • Reliability 4/5
  • Maintainer responsiveness 4/5
Ingrid Nilsson Platform engineer
Trusts with caveats Recommends

Our team uses it every day

Been running this for about a month now. Scoped the token to just what the agent needs and it respected that. Fine in production if you sandbox it.

Used for Answering support questions from the database

  • Setup & docs 4/5
  • Auth experience 4/5
  • Reliability 4/5
  • Maintainer responsiveness 3/5
Aditi Rao Senior developer
Trusts in production Recommends

Exactly what I needed from BigQuery

Installed it on a Friday, it was part of my workflow by Monday. Sign-in flow was painless and I never had to paste a key into a config file.

Used for Incident investigation

  • Setup & docs 4/5
  • Auth experience 3/5
  • Reliability 5/5
  • Maintainer responsiveness 5/5
Yuki Tanaka AI engineer
Trusts in production Recommends

Does what it says, no drama

Started with it as an experiment, now it is a fixture. I like that access goes through a proper sign-in instead of a long-lived secret on disk. Nothing to install, I just point the client at the URL. Running it with the read-only flag and have not missed write access. Happy to run it in production.

Used for Checking data quality after imports

  • Setup & docs 5/5
  • Auth experience 4/5
  • Reliability 5/5
  • Maintainer responsiveness 3/5

Write a review

Ran this server? Tell other teams how it went. You get one review per server. We email you a link to confirm it, then an editor checks it before it goes up. We never show your email.

How was it overall?

Would you trust it in production?
Would you recommend it to another team?

Score the details

Setup & docs
Auth experience
Reliability
Maintainer responsiveness

Tell other teams how it went

About you