{"_id":"@renzo.johnson/bigquery-mcp","_rev":"4-9590ee590e9e0c388bd8358b9bbf1a5f","name":"@renzo.johnson/bigquery-mcp","dist-tags":{"latest":"26.11.15"},"versions":{"26.11.14":{"name":"@renzo.johnson/bigquery-mcp","version":"26.11.14","keywords":["MCP","MCP server","Model Context Protocol","BigQuery","BigQuery MCP","Google BigQuery","SQL","Data warehouse","Google Cloud","AI","Claude","Copilot","Cursor","Codex","Gemini","mcp-server","modelcontextprotocol"],"author":{"url":"https://renzojohnson.com","name":"Renzo Johnson"},"license":"MIT","_id":"@renzo.johnson/bigquery-mcp@26.11.14","maintainers":[{"name":"renzo.johnson","email":"renzo.johnson@gmail.com"}],"homepage":"https://renzojohnson.com/contributions/bigquery-mcp","bugs":{"url":"https://renzojohnson.com/contact"},"bin":{"bigquery-mcp":"dist/server.js"},"dist":{"shasum":"a621c789a693ee33582786aa1727a77a53eae257","tarball":"https://registry.npmjs.org/@renzo.johnson/bigquery-mcp/-/bigquery-mcp-26.11.14.tgz","fileCount":4,"integrity":"sha512-vczF1vLHLk+Ar8zAH6+fWGw8N3MHhN0r0PTdg3o8wxxsheCJiQIEi1HfyiqTafMfhPtiE/EMJF+oLzNjsXM4RQ==","signatures":[{"sig":"MEQCIFTIDi79yyv2VQ7yNaGMzu6fkrEcTibUtJiCGt0+/rE6AiArpqwoAGNRKw6gY0YnT0kHgXcXYtfl12L0EfM7N0lPVA==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"},{"sig":"MEUCIBLWbiDNYVPW0rAS50wqoqtBGUN3/JdLNinX3hKcU/Y9AiEA9SK2tOEHjamyyvFdgAdZtG4ynZtWoKaxsvYvj8iq+f4=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":1141868},"_from":"file:/srv/www/projects/bigquery-mcp/npm/renzo.johnson-bigquery-mcp-26.11.14.tgz","engines":{"node":">=22"},"mcpName":"com.renzojohnson/bigquery-mcp","_npmUser":{"name":"renzo.johnson","email":"renzo.johnson@gmail.com"},"_resolved":"/srv/www/projects/bigquery-mcp/npm/renzo.johnson-bigquery-mcp-26.11.14.tgz","_integrity":"sha512-vczF1vLHLk+Ar8zAH6+fWGw8N3MHhN0r0PTdg3o8wxxsheCJiQIEi1HfyiqTafMfhPtiE/EMJF+oLzNjsXM4RQ==","_npmVersion":"12.2.2","description":"BigQuery MCP server for Claude Code, Cursor, Copilot and five more AI agents.","directories":{},"_nodeVersion":"26.13.1","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/bigquery-mcp_26.11.14_1794535047549_0.6645981732269401","host":"s3://npm-registry-packages-npm-production"}},"26.11.15":{"_id":"@renzo.johnson/bigquery-mcp@26.11.15","bin":{"bigquery-mcp":"dist/server.js"},"bugs":{"url":"https://renzojohnson.com/contact"},"dist":{"shasum":"36a3ecf68f749c29c4f4a57724ede9ee11fa6f6b","tarball":"https://registry.npmjs.org/@renzo.johnson/bigquery-mcp/-/bigquery-mcp-26.11.15.tgz","fileCount":6,"integrity":"sha512-BsY6vqi0Rp7evTKSR8sQAg6lfHfKCZpIZRtTNV7wGfF6wCUfSwoInq+mefVDH2hjHqIMiXgACkrQBmZKBeO28A==","signatures":[{"sig":"MEYCIQCjAPLSRAcfq9GKBU33w2Kxrkmzz+q8hNVfeoFJoKComAIhAJNY12J8uUYpGcA2wRaSUy/UW2joqFVBOQGdFneTZ2AU","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"},{"keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U","sig":"MEUCIQCuhtQummrGa82VBbOEpJ1XsJ8SchP4F46FMbqXQohruAIgF6lI3fbxo+JugIAHQKFyolCM9RRispq428erlIzsD5g="}],"unpackedSize":1141905},"name":"@renzo.johnson/bigquery-mcp","_from":"file:renzo.johnson-bigquery-mcp-26.11.15.tgz","author":{"url":"https://renzojohnson.com","name":"Renzo Johnson"},"engines":{"node":">=22"},"license":"MIT","mcpName":"com.renzojohnson/bigquery-mcp","version":"26.11.15","_npmUser":{"name":"renzo.johnson","email":"renzo.johnson@gmail.com"},"homepage":"https://renzojohnson.com/contributions/bigquery-mcp","keywords":["MCP","MCP server","Model Context Protocol","BigQuery","BigQuery MCP","Google BigQuery","SQL","Data warehouse","Google Cloud","AI","Claude","Copilot","Cursor","Codex","Gemini","mcp-server","modelcontextprotocol"],"_resolved":"/Users/user/Desktop/renzo.johnson-bigquery-mcp-26.11.15.tgz","_integrity":"sha512-BsY6vqi0Rp7evTKSR8sQAg6lfHfKCZpIZRtTNV7wGfF6wCUfSwoInq+mefVDH2hjHqIMiXgACkrQBmZKBeO28A==","_npmVersion":"11.12.1","description":"BigQuery MCP server for Claude Code, Cursor, Copilot and five more AI agents. mcprush.com-45569233d2e038a123849647","directories":{},"maintainers":[{"name":"renzo.johnson","email":"renzo.johnson@gmail.com"}],"_nodeVersion":"25.9.0","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"host":"s3://npm-registry-packages-npm-production","tmp":"tmp/bigquery-mcp_26.11.15_1794753183225_0.5953112535380757"}}},"time":{"created":"2026-11-13T01:55:19.650Z","modified":"2026-11-15T14:33:03.488Z","0.0.0-stage":"2026-11-13T01:55:19.650Z","26.11.14":"2026-11-13T01:57:27.694Z","26.11.15":"2026-11-15T14:33:03.337Z"},"bugs":{"url":"https://renzojohnson.com/contact"},"author":{"url":"https://renzojohnson.com","name":"Renzo Johnson"},"license":"MIT","homepage":"https://renzojohnson.com/contributions/bigquery-mcp","keywords":["MCP","MCP server","Model Context Protocol","BigQuery","BigQuery MCP","Google BigQuery","SQL","Data warehouse","Google Cloud","AI","Claude","Copilot","Cursor","Codex","Gemini","mcp-server","modelcontextprotocol"],"description":"BigQuery MCP server for Claude Code, Cursor, Copilot and five more AI agents. mcprush.com-45569233d2e038a123849647","maintainers":[{"name":"renzo.johnson","email":"renzo.johnson@gmail.com"}],"readme":"# BigQuery MCP\n\n[![npm](https://img.shields.io/npm/v/@renzo.johnson/bigquery-mcp?label=npm&color=red)](https://www.npmjs.com/package/@renzo.johnson/bigquery-mcp)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n\n**BigQuery MCP server for Claude Code, Cursor, Copilot and five more AI agents.** This is the MCP server from the BigQuery MCP VS Code extension, packaged to run with `npx` in any MCP client.\n\nRequires Node.js 22 or newer.\n\n```bash\nnpx -y @renzo.johnson/bigquery-mcp\n```\n\nThe server speaks MCP over stdio, so you normally let your AI agent start it, as below.\n\n## Claude Code\n\n```bash\nclaude mcp add bigquery-mcp -- npx -y @renzo.johnson/bigquery-mcp\n```\n\nOr add it to `.mcp.json` in your project (or `~/.claude.json` for every project):\n\n```json\n{\n  \"mcpServers\": {\n    \"bigquery-mcp\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@renzo.johnson/bigquery-mcp\"],\n      \"env\": {\n        \"GOOGLE_APPLICATION_CREDENTIALS\": \"/path/to/service-account.json\"\n      }\n    }\n  }\n}\n```\n\n## Cursor\n\nAdd the same block to `~/.cursor/mcp.json` (or `.cursor/mcp.json` in a project):\n\n```json\n{\n  \"mcpServers\": {\n    \"bigquery-mcp\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@renzo.johnson/bigquery-mcp\"],\n      \"env\": {\n        \"GOOGLE_APPLICATION_CREDENTIALS\": \"/path/to/service-account.json\"\n      }\n    }\n  }\n}\n```\n\n## Credentials\n\nThe server signs in to Google in this order:\n\n| Option | Environment | Best for |\n|--------|-------------|----------|\n| **OAuth user** | `GOOGLE_OAUTH_CLIENT_ID`, `GOOGLE_OAUTH_CLIENT_SECRET`, `GOOGLE_OAUTH_REFRESH_TOKEN` (all three) | Personal Google accounts |\n| **Service account or saved credentials** | `GOOGLE_APPLICATION_CREDENTIALS` = path to a JSON key | Servers, Workspace admins |\n| **gcloud** | none: run `gcloud auth application-default login` once | Developers with the Google Cloud CLI |\n\nSetting only some of the three OAuth variables stops the server with an error that names the missing ones. Enable the BigQuery API in your Google Cloud project.\n\nOptional settings:\n\n| Variable | What it does |\n|----------|--------------|\n| `BIGQUERY_MCP_PROJECT_ID` | Google Cloud project ID used when a request does not name one |\n| `BIGQUERY_MCP_MAX_BYTES_BILLED` | Largest number of bytes a query may scan (default 1000000000) |\n\nSet **bigqueryMcp.projectId** to the project that runs your queries. `bq_query` runs only `SELECT` statements and dry-runs each one first; a query that would scan more than **bigqueryMcp.maxBytesBilled** (1 GB by default) is refused instead of billed.\n\n## Available Tools (5)\n\n| Tool | What It Does | Example Prompt |\n|------|-------------|----------------|\n| `bq_list_datasets` | Datasets in a project | \"List my datasets\" |\n| `bq_list_tables` | Tables and views in a dataset | \"What tables are in analytics?\" |\n| `bq_get_table` | Schema, row count and size | \"Show the schema of analytics.events\" |\n| `bq_query` | Run a SELECT, after a dry-run cost check | \"Orders per day last week\" |\n\n### Safety\n\nBigQuery MCP runs SELECT queries only, with a byte limit. Every query is dry-run first. Anything other than a single SELECT, or a query that would scan more than `BIGQUERY_MCP_MAX_BYTES_BILLED` (1 GB by default), is refused before it runs or bills.\n\n## VS Code\n\nPrefer a setup wizard that registers the server with eight agents for you? Install the [BigQuery MCP extension](https://open-vsx.org/extension/mercurial/bigquery-mcp) instead (also on the [VS Code Marketplace](https://marketplace.visualstudio.com/items?itemName=mercurial.bigquery-mcp)). Use one or the other, not both.\n\n## Links\n\n- [Documentation](https://renzojohnson.com/contributions/bigquery-mcp)\n- [Report an Issue](https://renzojohnson.com/contact)\n\n---\n\n**By [Renzo Johnson](https://renzojohnson.com/contributions/bigquery-mcp)**\n","readmeFilename":"README.md"}