bigquery-mcp — Claude Code MCP server: setup
This MCP server lets AI agents inspect Google BigQuery schemas, list tables, and run SQL queries when direct data access is needed.
claude mcp add bigquery-mcp -- uvx sl-bigquery-mcpWhat bigquery-mcp does
bigquery-mcp connects an AI agent to Google BigQuery through MCP. It exposes resources for available tables and individual table schemas, while the query tool runs BigQuery SQL and returns the result. The list_tables and get_schema tools can be enabled as configuration options.
You need a Google Cloud Project with BigQuery enabled and permission to submit jobs, plus gcloud and uv. Authenticate the local environment with gcloud auth application-default login, then run the server through uvx sl-bigquery-mcp. Queries will fail without a project that can submit BigQuery jobs.
For Claude Code, add the server with claude mcp add bigquery-mcp -- uvx sl-bigquery-mcp. Codex and Gemini CLI have their own add commands; Cursor and GitHub Copilot use MCP configuration entries that start uvx.
What it helps with
- list available BigQuery tables
- inspect a table schema
- run SQL against BigQuery data
- answer data questions through an AI agent
Example prompts for the agent
- List the tables available in the connected BigQuery dataset.
- Inspect the schema of
project.dataset.tableand explain its fields. - Run a SQL query against the data and return the results with a short explanation.
How to install bigquery-mcp
Platform CLI
claude mcp add bigquery-mcp -- uvx sl-bigquery-mcpuvx runs the command named after the package; if the README names another one, use uvx --from sl-bigquery-mcp <command>
Platform CLI
codex mcp add bigquery-mcp -- uvx sl-bigquery-mcpuvx runs the command named after the package; if the README names another one, use uvx --from sl-bigquery-mcp <command>
Config file
{
"mcpServers": {
"bigquery-mcp": {
"command": "uvx",
"args": [
"sl-bigquery-mcp"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from sl-bigquery-mcp <command>
Config file
{
"servers": {
"bigquery-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"sl-bigquery-mcp"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from sl-bigquery-mcp <command>
Platform CLI
gemini mcp add bigquery-mcp uvx sl-bigquery-mcpuvx runs the command named after the package; if the README names another one, use uvx --from sl-bigquery-mcp <command>
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about bigquery-mcp
How do I install bigquery-mcp in Claude Code?
Run claude mcp add bigquery-mcp -- uvx sl-bigquery-mcp.
What does bigquery-mcp do?
It connects an AI agent to Google BigQuery, exposes table and schema information, and executes SQL through the query tool.
What is required to run bigquery-mcp?
You need a Google Cloud Project with BigQuery enabled and job-submission permission, along with Google Cloud CLI and uv. Authenticate with gcloud auth application-default login first.
