{"type":"mcp_server","name":"mcp-bigquery-server","description":"This repository provides a server enabling LLMs like Claude to interact directly with BigQuery data using natural language. It leverages the Model Context Protocol for secure and efficient AI-database communication.","category":"Database","language":"JavaScript","stars":142,"forks":7,"owner":"ergut","github_url":"https://github.com/ergut/mcp-bigquery-server","homepage":null,"setup":"## Setup\n\n**Option 1: Quick Install via Smithery (Recommended)**\n\nTo install BigQuery MCP Server for Claude Desktop automatically via [Smithery](https://smithery.ai/protocol/@ergut/mcp-bigquery-server), run this command in your terminal:\n\n```bash\nnpx @smithery/cli install @ergut/mcp-bigquery-server --client claude\n```\nThe installer will prompt you for:\n\n- Your Google Cloud project ID\n- BigQuery location (defaults to us-central1)\n\nOnce configured, Smithery will automatically update your Claude Desktop configuration and restart the application.\n\n**Option 2: Manual Setup**\n\nIf you prefer manual configuration or need more control:\n\n1. **Authenticate with Google Cloud** (choose one method):\n   - Using Google Cloud CLI (great for development):\n     ```bash\ngcloud auth application-default login\n     ```\n   - Using a service account (recommended for production):\n     ```bash\n# Save your service account key file and use --key-file parameter\n# Remember to keep your service account key file secure and never commit it to version control\n     ```\n\n2. **Add to your Claude Desktop config**\n   Add this to your `claude_desktop_config.json`:\n\n   - Basic configuration:\n     ```json\n     {\n       \"mcpServers\": {\n         \"bigquery\": {\n           \"command\": \"npx\",\n           \"args\": [\n             \"-y\",\n             \"@ergut/mcp-bigquery-server\",\n             \"--project-id\",\n             \"your-project-id\",\n             \"--location\",\n             \"us-central1\"\n           ]\n         }\n       }\n     }\n     ```\n\n   - With service account:\n     ```json\n     {\n       \"mcpServers\": {\n         \"bigquery\": {\n           \"command\": \"npx\",\n           \"args\": [\n             \"-y\",\n             \"@ergut/mcp-bigquery-server\",\n             \"--project-id\",\n             \"your-project-id\",\n             \"--location\",\n             \"us-central1\",\n             \"--key-file\",\n             \"/path/to/service-account-key.json\"\n           ]\n         }\n       }\n     }\n     ```\n\n\n3. **Start chatting!** \n   Open Claude Desktop and start asking questions about your data.","tools":"## Available Tools\n\n1.  Run SQL queries (by just asking questions in plain English).\n2.  Access tables and materialized views (in your datasets).\n3.  Explore dataset schemas (with clear labeling of resource types).\n4.  Analyze data (within safe limits, 1GB query limit by default).\n5.  Keep your data secure (read-only access).","faq":null,"created_at":"2024-12-03T19:57:59+00:00","updated_at":"2025-03-28T02:13:39+00:00","source_url":"https://model-context-protocol.com/servers/llm-bigquery-data-access-server","related_articles":[]}