How to Configure JetBrains AI Bigquery MCP Server
To set up a jetbrains ai bigquery mcp server, link your IDE to a local server process. Next, give that process a Google Cloud role with read rights for your tables. Many teams start by using a broad admin key to get things working fast. That shortcut lets the AI agent read sensitive tables or change data by mistake. How the jetbrains ai bigquery mcp server setup works Your code editor runs an AI chat client on your laptop. That client talks to a local MCP server process over standard input an
Your coding agents run with your access.
Claude Code reaches prod with a developer's credentials, and approval prompts get clicked through. hoop.dev checks every query, masks sensitive data, and holds risky changes for a human.
To set up a jetbrains ai bigquery mcp server, link your IDE to a local server process. Next, give that process a Google Cloud role with read rights for your tables. Many teams start by using a broad admin key to get things working fast. That shortcut lets the AI agent read sensitive tables or change data by mistake.
How the jetbrains ai bigquery mcp server setup works
Your code editor runs an AI chat client on your laptop. That client talks to a local MCP server process over standard input and output. The server translates AI prompts into standard SQL queries for your data warehouse. It then sends those queries to Google Cloud using your local cloud login.
Google Cloud checks the cloud role tied to your local user or service key. You can set up this role at the project level or the dataset level. Most teams create a custom role that only allows running jobs and reading tables. The server runs the query, gets the rows back, and hands them to the IDE.
How to scope cloud roles for your IDE
A safe setup starts with a dedicated service identity for your AI tools. Never reuse your personal admin login or a production app key for editor tools. Grant this new identity read rights only on the datasets your team needs.
You should also set query size limits in your Google Cloud project settings. An AI assistant can write a bad join that scans terabytes of data in seconds. Project quotas stop a single bad prompt from running up a huge cloud bill. Keep write and delete permissions off this role so the agent cannot drop tables.
What native setup solves and what it misses
Native Google Cloud roles do a good job of controlling who can log in. They also control which datasets and tables a specific user or key can reach. If an AI tool tries to read a blocked dataset, Google Cloud stops the job.
BigQuery IAM + Kubernetes API Server Access: architecture patterns and best practices
Continue reading? Get the full guide.
Free. No spam. Unsubscribe anytime.
Still, static cloud roles cannot check what an individual SQL query does in flight. Once a role grants access to a table, the AI reads every row and column by default. If that table holds customer emails, phone numbers, or card numbers, the AI gets them. The local server also saves static keys on laptops, which creates a theft risk.
Cloud logs show that a service key ran a query, not which human asked for it. Teams also lack a way to require human approval before a risky query runs. To fix this, you need controls that inspect queries and mask fields like national IDs.
Check database and API queries on the wire
Identity tools, roles, and network rules decide who opens a session. Setup alone cannot check what each query does or mask sensitive values in a response once a session starts. When workflows touch Postgres, MySQL, SQL Server, MongoDB, ClickHouse, Kubernetes APIs, SSH, or internal HTTP APIs, hoop.dev runs beside those services as an open-source proxy, a sidecar for your Postgres or API. It inspects requests coming in and results going back on the wire.
Your login details and client tools stay as they are while hoop.dev guardrails refuse bad deletes or drops before they run. On responses, hoop.dev data masking rewrites matched sensitive values in memory. Furthermore, hoop.dev holds SOC 2 Type II, is MIT licensed, and writes every query and decision to an audit trail that generates evidence for HIPAA, GDPR, and PCI DSS. See the source on GitHub.
Frequently asked questions
Can the AI assistant modify or delete my BigQuery tables?
It can if you give the server a role with write or admin rights. Always assign a read-only role so the agent can only select data and run jobs.
Where do the Google Cloud keys live in a standard setup?
In a standard local setup, the credentials live in a file on the developer laptop. The local MCP process reads this file to log in to Google Cloud.
How do I stop the AI from pulling sensitive customer columns?
In native Google Cloud, you must set up column-level security or build separate views. Otherwise, any role with table read rights will pull every column in that table by default.
Related guides
In this post