Add the BigQuery MCP server to Cursor

Config last verified Jun 1, 2026

The exact config to run BigQuery in Cursor — paste it in, restart, and the tools load.

Prerequisites

Cursor installed.
BIGQUERY_PROJECT — Default Google Cloud project ID used for all BigQuery operations.

Setup

1. Open `~/.cursor/mcp.json`

2. Add this configuration

Add to ~/.cursor/mcp.json

~/.cursor/mcp.json

json

{
  "mcpServers": {
    "bigquery": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "BIGQUERY_PROJECT",
        "us-central1-docker.pkg.dev/database-toolbox/toolbox/toolbox:latest",
        "--prebuilt",
        "bigquery",
        "--stdio"
      ],
      "env": {
        "BIGQUERY_PROJECT": "<BIGQUERY_PROJECT>"
      }
    }
  }
}

3. Restart Cursor and confirm the BigQuery tools load.

Gotchas

Cursor keeps MCP servers under an "mcpServers" object in ~/.cursor/mcp.json for global use, and also reads a project-scoped .cursor/mcp.json so a repository can ship its own servers. Remote servers are configured with a bare "url" field and connect natively, with OAuth handled in-app when a server requires it.

← Back to the BigQuery MCP server