A FastMCP server for securely accessing BigQuery datasets with intelligent caching, schema evolution tracking, and query analytics via Supabase integration.
mcp-bigquery-server is an MCP project maintained in the mousten/mcp-bigquery-server repository. The maintainer describes its purpose as “A FastMCP server for securely accessing BigQuery datasets with intelligent caching, schema evolution tracking, and query analytics via Supabase integration”. Read the project documentation for the complete scope.
The project provides a local client configuration using /path/to/your/project/.venv/bin/mcp-bigquery. Follow the repository’s build and installation steps before copying it, and replace example paths with the paths on your own computer.
The example declares PROJECT_ID, LOCATION, KEY_FILE, SUPABASE_URL, SUPABASE_SERVICE_KEY, DEFAULT_USER_ID. Secret-looking values have been replaced with placeholders. Required and optional labels are shown only when the documentation states them.
Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-08.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| resources | //list - List all BigQuery resources |
| bigquery | //{project}/{dataset}/{table} - Access specific table metadata |
| execute_bigquery_sql | Execute a read-only SQL query with intelligent caching |
| Parameters | user_id |
| get_datasets | Get list of datasets with metadata |
| get_tables | Get tables in a dataset with column documentation |
| get_table_schema | Get comprehensive table schema details |
| get_query_suggestions | Get AI-powered query recommendations |
| explain_table | Get comprehensive table documentation and business context |
| analyze_query_performance | Analyze historical query performance patterns |
| get_schema_changes | Track schema evolution and changes over time |
| manage_cache | Comprehensive cache management operations |
| health_check | System health check including BigQuery, Supabase, and cache status |
{
"mcpServers": {
"mcp-bigquery": {
"command": "/path/to/your/project/.venv/bin/mcp-bigquery",
"args": [
"--transport",
"stdio"
],
"env": {
"PROJECT_ID": "your-project-id",
"LOCATION": "US",
"KEY_FILE": "YOUR_KEY_FILE",
"SUPABASE_URL": "https://your-project.supabase.co",
"SUPABASE_SERVICE_KEY": "YOUR_SUPABASE_SERVICE_KEY",
"DEFAULT_USER_ID": "your-user-id"
}
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
| Variable | Description | Required |
|---|---|---|
| PROJECT_ID | Declared in the maintainer’s client configuration. | Check documentation |
| LOCATION | Declared in the maintainer’s client configuration. | Check documentation |
| KEY_FILE | Declared in the maintainer’s client configuration. | Optional |
| SUPABASE_URL | Declared in the maintainer’s client configuration. | Check documentation |
| SUPABASE_SERVICE_KEY | Declared in the maintainer’s client configuration. | Check documentation |
| DEFAULT_USER_ID | Declared in the maintainer’s client configuration. | Optional |
Inspect PostgreSQL schemas and run read-only queries with the archived MCP reference server. Review its maintenance status before choosing it.
Connect the Notion MCP server to search workspace content and work with pages and databases through Notion’s hosted OAuth service.
Use the Supabase MCP server to inspect database schemas, query project data and retrieve docs through a project-scoped connection.
Query, modify and analyse local SQLite databases in conversation — the fastest way to chat with a data file.
Metabase ships its own MCP endpoint — search your BI content, build and run queries, and save questions and dashboards without leaving the chat.
Official MongoDB server covering data, schemas and Atlas management — from find queries to spinning up clusters.