BigQuery Analysis
About
Enables safe SQL query execution on Google BigQuery datasets with built-in safeguards that prevent data manipulation and limit query size to 1 TB.
Details
- Author
- gotalab
- Repository
- gotalab/bigquery-analysis-mcp-server
- GitHub stars
- 1
- Downloads
- 342
- Categories
- Database, Other, AI, Design, Developer Tools, Search, Security
- Tags
- #data-science
Jump to
- Query validation (dry run) with processing size estimation
- Safe query execution: only SELECT queries under 1TB
- Rejects DML statements (data modification queries)
- Returns results in structured JSON format
- Prevents accidental large data processing (>1TB)
- Developed with Node.js and requires Google Cloud authentication
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
BigQuery AnalysisCommand (node, npx, python, etc.)nodeArguments-
Argument 1
/path/to/bigquery-server/build/index.js
Environment-
GOOGLE_APPLICATION_CREDENTIALS
/path/to/service-account-key.json
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
-
Argument 1
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
To use with Claude Desktop, add the server configuration:
npm install
dry_run_query
Perform a dry run of a BigQuery query. Validates the query and estimates its processing size. Checks query size against the 1TB limit.
run_query_with_validation
Run a BigQuery query with validation. Detects and rejects DML statements (data modification queries), rejects data processing over 1TB, and executes queries that pass validation, returning results.
- dry_run_query - Perform a dry run of a BigQuery query
- Validates the query and estimates its processing size
- Checks query size against the 1TB limit
- run_query_with_validation - Run a BigQuery query with validation
- Detects and rejects DML statements (data modification queries)
- Rejects data processing over 1TB
- Executes queries that pass validation and returns results
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"bigquery analysis": {
"env": {
"GOOGLE_APPLICATION_CREDENTIALS": "/path/to/service-account-key.json"
},
"args": [
"/path/to/bigquery-server/build/index.js"
],
"command": "node"
}
}
}Linux
{
"env": {
"GOOGLE_APPLICATION_CREDENTIALS": "/path/to/service-account-key.json"
},
"args": [
"/path/to/bigquery-server/build/index.js"
],
"command": "node"
}Macos
{
"env": {
"GOOGLE_APPLICATION_CREDENTIALS": "/path/to/service-account-key.json"
},
"args": [
"/path/to/bigquery-server/build/index.js"
],
"command": "node"
}Windows
{
"env": {
"GOOGLE_APPLICATION_CREDENTIALS": "/path/to/service-account-key.json"
},
"args": [
"/path/to/bigquery-server/build/index.js"
],
"command": "node"
}This server is an MCP server for executing SQL queries against Google BigQuery, providing the following features:
- Query validation (dry run): Verifies if a query is valid and estimates its processing size
- Safe query execution: Only runs SELECT queries under 1TB (prevents data modifications)
- JSON-formatted results: Returns query results in structured JSON format
-
dry_run_query- Perform a dry run of a BigQuery query
- Validates the query and estimates its processing size
- Checks query size against the 1TB limit
run_query_with_validation- Run a BigQuery query with validation
- Detects and rejects DML statements (data modification queries)
- Rejects data processing over 1TB
- Executes queries that pass validation and returns results
- Node.js (v16 or higher)
- Google Cloud authentication setup (gcloud CLI or service account)
To use with Claude Desktop, add the server configuration:
MacOS:~/Library/Application Support/Claude/claude_desktop_config.json
Windows:%APPDATA%/Claude/claude_desktop_config.json
{ "mcpServers": { "bigquery-analysis-server": { "command": "/path/to/bigquery-analysis-server/build/index.js" } } }
Since MCP servers communicate over stdio, debugging can be challenging. We recommend using theMCP Inspector:
The Inspector will provide a URL to access debugging tools in your browser.
This server uses Google Cloud authentication. Set up authentication using one of the following methods:
export GOOGLE_APPLICATION_CREDENTIALS="/path/to/service-account-key.json"
dry_run_query("SELECT FROM bigquery-public-data.samples.shakespeare LIMIT 10")
run_query_with_validation("SELECT word, word_count FROM bigquery-public-data.samples.shakespeare WHERE corpus='hamlet' LIMIT 10")
BigQueryでSQLクエリを実行するためのMCPサーバーです。クエリの検証（ドライラン）と実行を行い、1TB以上のデータ処理や変更系クエリ（DML）を防止する安全機能を備えています。
このサーバーはGoogle BigQueryに対してSQLクエリを実行するためのMCPサーバーで、以下の機能を提供します：
- クエリの検証（ドライラン）：クエリが有効かどうかを確認し、処理サイズを見積もる
- 安全なクエリ実行：1TB以下のSELECTクエリのみを実行（データ変更を防止）
- 結果のJSON形式での返却：クエリ結果を構造化されたJSONで返す
- クエリの検証と処理サイズの見積もりを行う
- 1TBの制限に対してクエリサイズをチェック
run_query_with_validation- 検証付きでBigQueryクエリを実行
- DML文（データ変更クエリ）を検出して拒否
- 1TB以上のデータ処理を拒否
- 検証に通過したクエリを実行し結果を返す
- Node.js（v16以上）
- Google Cloud認証設定（gcloud CLIまたはサービスアカウント）
MacOS:~/Library/Application Support/Claude/claude_desktop_config.json
Windows:%APPDATA%/Claude/claude_desktop_config.json
{ "mcpServers": { "bigquery": { "command": "node", "args": ["/path/to/bigquery-server/build/index.js"] } } }
MCPサーバーは標準入出力（stdio）を介して通信するため、デバッグが難しい場合があります。MCP Inspectorの使用をお勧めします：
InspectorはブラウザでデバッグツールにアクセスするためのURLを提供します。
このサーバーはGoogle Cloud認証情報を使用します。以下のいずれかの方法で認証を設定してください：
export GOOGLE_APPLICATION_CREDENTIALS="/path/to/service-account-key.json"
dry_run_query("SELECT FROM bigquery-public-data.samples.shakespeare LIMIT 10")
run_query_with_validation("SELECT word, word_count FROM bigquery-public-data.samples.shakespeare WHERE corpus='hamlet' LIMIT 10")
Access and cache Google Cloud BigQuery metadata.
Explore, query, and manage data in Google BigQuery.
Access Google BigQuery to understand dataset structures and execute SQL queries.
A secure, self-hosted Model Context Protocol (MCP) server for Google BigQuery. Hard table allowlists, per-query scan ceilings, built-in rate limiting, and predictable costs on Cloud Run. Works with Claude, ChatGPT, Cursor, Gemini, and any MCP-compatible AI agent.
Unified MCP server giving AI coding agents direct access to your databases: 70+ SQL databases via SqlKit (PostgreSQL, MySQL, SQL Server, SQLite, ClickHouse, Snowflake, BigQuery) and NoSQL via DocKit (Elasticsearch, MongoDB, DynamoDB). Local-first: credentials never leave your machine, read-only by default, 79 tools.
Turn SQL templates + YAML into REST APIs and MCP tools — one static binary with embedded DuckDB (Parquet, Postgres, BigQuery, S3 and 50+ sources), per-tool RBAC, and DuckLake caching.
LangGrant turns AI data questions into reusable, governed Data Plans, joining data across multiple databases (Snowflake, Oracle, Postgres, BigQuery and more) and plugging into your MCP tools.
Securely access BigQuery datasets with intelligent caching, schema tracking, and query analytics via Supabase integration.
Create and monitor AI marketing-automation tasks across Google Ads, GA4, BigQuery and more, from any MCP client.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
