drio
Open app

BigQuery MCP Server

Source

Catalog onlyCatalog onlySTDIO

Overview

BigQuery MCP Server is a Model Context Protocol (MCP) server designed to facilitate access to Google BigQuery, enabling Large Language Models (LLMs) to comprehend BigQuery dataset structures and execute SQL queries.

To use the server, you can either install it locally or run it in a Docker container. After installation, configure it with your Google Cloud project ID and authentication credentials, then use the provided tools to execute queries or list datasets and tables.

  • Supports Application Default Credentials and service account key files for authentication. - Tools for executing SQL queries, listing datasets, and retrieving table information. - Security features to ensure only read-only access and prevent excessive costs.
  1. Executing SQL queries to retrieve data from BigQuery.
  2. Listing all datasets and tables for data exploration.
  3. Validating queries without execution to estimate costs.

Add to your AI client

Use these steps to connect BigQuery MCP Server in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "bigquery-mcp-server-takuya0206": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-bigquery-mcp-server-takuya0206"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "bigquery-mcp-server-takuya0206": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-bigquery-mcp-server-takuya0206"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "bigquery-mcp-server-takuya0206": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-bigquery-mcp-server-takuya0206"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "bigquery-mcp-server-takuya0206": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-bigquery-mcp-server-takuya0206"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "bigquery-mcp-server-takuya0206": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-bigquery-mcp-server-takuya0206"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "bigquery-mcp-server-takuya0206": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-bigquery-mcp-server-takuya0206"
      ]
    }
  }
}

FAQ

**What types of queries can I execute?**

Only read-only (SELECT) queries are allowed to ensure data security.

**How do I authenticate?**

You can authenticate using Application Default Credentials or a service account key file.

**Is there a limit on query processing?**

Yes, there is a default limit of 500GB for query processing to prevent excessive costs.7:["$","div",null,{"className":"container mx-auto flex flex-col gap-4","children":["$L26","$L27",["$","$L28",null,{"currentProject":{"id":3106,"uuid":"2ce027ca-4908-4945-b25f-6faad4a9ff51","name":"bigquery-mcp-server","title":"BigQuery MCP Server","description":"","avatar_url":"https://avatars.githubusercontent.com/u/22774683?v=4","created_at":"2025-03-18T02:51:07.678Z","updated_at":"2025-03-18T16:35:28.955Z","status":"created","author_name":"takuya0206","author_avatar_url":"https://avatars.githubusercontent.com/u/22774683?v=4","tags":"[]","category":"research-and-data","is_featured":false,"sort":1,"url":"https://github.com/takuya0206/bigquery-mcp-server","target":"_self","content":"$29","summary":"$2a","img_url":null,"type":null,"metadata":"{\"star\":\"0\",\"license\":\"MIT license\",\"language\":\"TypeScript\",\"is_official\":false,\"latest_commit_time\":\"2025-04-02 09:36:02\"}","user_uuid":null,"tools":null,"sse_url":null,"sse_provider":null,"sse_params":null,"is_official":false,"server_command":null,"server_params":null,"server_config":null,"allow_call":false,"is_innovation":false,"is_dxt":false,"dxt_manifest":null,"dxt_file_url":null,"is_audit":false},"randomProjects":[],"currentServerKey":"$undefined"}]]}]

Research and data