bigquery-mcp
Provides tools for querying and analyzing BigQuery datasets across multiple Google Cloud projects, supporting operations like listing datasets, tables, analyzing columns, and executing SQL queries with security controls.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@bigquery-mcplist datasets in analytics-prod"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
BigQuery MCP Server
MCP server for secure BigQuery access across multiple Google Cloud projects.
Features
Multi-Project Access - Query across BigQuery projects with pattern matching
Advanced Analytics - Column analysis, data quality checks, schema exploration
Security Controls - SQL validation, query limits, read-only operations
CLI Configuration - Command-line arguments with config file fallback
Docker Support - Containerized deployment for easy integration
Related MCP server: bq-readonly-mcp
Documentation
Full documentation available at aicayzer.github.io/bigquery-mcp
Quick Start
Prerequisites
Python 3.11+
Google Cloud SDK
Docker (optional)
Authentication
gcloud auth application-default loginInstallation
git clone https://github.com/aicayzer/bigquery-mcp.git
cd bigquery-mcp
pip install -r requirements.txtMCP Client Setup
Claude Desktop
Add to ~/.config/claude/claude_desktop_config.json:
{
"mcpServers": {
"bigquery": {
"command": "docker",
"args": [
"run", "--rm", "-i",
"--volume", "/Users/YOUR_USERNAME/.config/gcloud:/home/mcpuser/.config/gcloud:ro",
"--volume", "/ABSOLUTE/PATH/TO/bigquery-mcp/logs:/app/logs",
"bigquery-mcp:latest",
"python", "src/server.py",
"--project", "your-project:*",
"--billing-project", "your-project"
]
}
}
}Cursor IDE
Add to MCP settings:
{
"bigquery": {
"command": "docker",
"args": [
"run", "--rm", "-i",
"--volume", "/Users/YOUR_USERNAME/.config/gcloud:/home/mcpuser/.config/gcloud:ro",
"bigquery-mcp:latest",
"python", "src/server.py",
"--project", "your-project:*",
"--billing-project", "your-project"
]
}
}Usage
CLI
# Single project
python src/server.py --project "your-project:*" --billing-project "your-project"
# Multiple projects with patterns
python src/server.py \
--project "analytics-prod:user_*,session_*" \
--project "logs-prod:application_*" \
--billing-project "my-billing-project"Docker
docker build -t bigquery-mcp .
docker run -v ~/.config/gcloud:/home/mcpuser/.config/gcloud:ro bigquery-mcp \
python src/server.py --project "your-project:*" --billing-project "your-project"Tools
list_projects()- List configured BigQuery projectslist_datasets(project)- List datasets in a projectlist_tables(dataset, table_type)- List tables in a datasetanalyze_table(table)- Get table structure and statisticsanalyze_columns(table, columns, sample_size)- Deep column analysisexecute_query(query, format, limit, timeout)- Execute SELECT queries
Configuration
CLI Arguments
python src/server.py \
--project "analytics-prod:user_*,session_*" \
--project "logs-prod:application_*" \
--billing-project "my-billing-project" \
--log-level INFO \
--timeout 20 \
--max-limit 50000Config File (Optional)
bigquery:
billing_project: "your-project"
location: "EU"
projects:
- project_id: "analytics-prod"
datasets: ["user_*", "session_*"]
- project_id: "logs-prod"
datasets: ["application_*"]Contributing
Fork the repository
Create a feature branch from
developMake your changes with tests
Submit a pull request to
develop
License
MIT License - see LICENSE file.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/aicayzer/bigquery-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server