# Google BigQuery MCP server > List datasets, inspect tables and run SQL queries in Google BigQuery projects, with job status and cancellation. - Listing: https://mcp.tc/i/bigquery - Connect: use the server's own URL `https://bigquery.googleapis.com/mcp` (OAuth sign-in at the server); clients connect to it directly. The listing link is a page, not an MCP endpoint. - Type: remote (Streamable HTTP) - Auth: OAuth sign-in - Category: [Databases & Backend](https://mcp.tc/c/databases) - Vendor: Google Cloud - Verified: yes, mcp.tc checked that this is the official server (https://mcp.tc/verify). It says who runs the server, not that it is safe. - Homepage: ## About Connects an assistant to Google BigQuery. It can list datasets and tables, read their metadata (including BigLake namespaces and tables), run SQL queries, fetch paged results and check or cancel query jobs. It runs as a hosted streamable HTTP endpoint at bigquery.googleapis.com/mcp. Access uses Google OAuth 2.0 and IAM permissions on the target project. The read-only SQL tool is limited to SELECT statements, while the general SQL tool can run statements that change data. ## What it can do - List dataset IDs and BigLake namespaces in a project - Read metadata for datasets and tables - List table IDs in a dataset - Run read-only SELECT queries - Run any SQL statement, including writes and DDL - Page through results of long-running query jobs - Check job status and cancel running jobs ## Tools (9) - `list_dataset_ids`: List BigQuery dataset IDs and BigLake namespaces in a project, with pagination. (read-only) - `get_dataset_info`: Get metadata about a BigQuery dataset or BigLake namespace. (read-only) - `list_table_ids`: List table IDs in a dataset or BigLake namespace, with pagination. (read-only) - `get_table_info`: Get metadata about a BigQuery table or BigLake table. (read-only) - `execute_sql_readonly`: Run a read-only SELECT query in the project and return the result. (read-only) - `execute_sql`: Run any BigQuery SQL, including INSERT, UPDATE, DELETE, CREATE and ML functions. (can modify or delete data) - `get_query_results`: Poll or paginate results of a query job by job ID. (read-only) - `cancel_job`: Cancel a running BigQuery job. (can modify or delete data) - `get_job`: Get status, statistics and configuration of a BigQuery job. (read-only) ## Example prompts - "List the datasets in my project my-analytics-prod" - "Show the schema of the orders table in the sales dataset" - "Run a query for daily signups over the last 30 days" - "Check the status of my last BigQuery job and cancel it if it is still running" ## Install ### Claude Code 1. Run this in a terminal, in your project folder: ```bash claude mcp add --transport http bigquery https://bigquery.googleapis.com/mcp ``` 2. Start Claude Code, type `/mcp`, pick **bigquery** and choose **Authenticate**. A browser window opens for the Google Cloud sign-in. Add `--scope user` to make it available in every project, not just this one. ### Claude Desktop 1. Open **Settings → Connectors** and click **Add custom connector**. 2. Name it **Google BigQuery** and paste this URL: ```url https://bigquery.googleapis.com/mcp ``` 3. Click **Add**, then **Connect**, and sign in when Google Cloud asks. Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too. ### claude.ai 1. Open the connector form on claude.ai. This button fills in the name and URL for you: [Add to claude.ai]() (opens connector settings) 2. Check that the URL reads `https://bigquery.googleapis.com/mcp` and click **Add**. 3. Click **Connect** and sign in when Google Cloud asks. Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**. ### ChatGPT 1. On chatgpt.com, open **Settings → Security and login** and turn on **Developer mode**. 2. Go to `chatgpt.com/plugins` and click **+** to create an app for a remote MCP server. 3. Paste `https://bigquery.googleapis.com/mcp` as the server URL and choose **OAuth**. ChatGPT sends you to Google Cloud to sign in. Developer mode is available on the web for Plus, Pro, Business, Enterprise and Education accounts. ### Cursor [Add to Cursor]() (opens Cursor) Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project): `mcp.json`: ```json { "mcpServers": { "bigquery": { "url": "https://bigquery.googleapis.com/mcp" } } } ``` Cursor shows **Needs login** next to the server. Click it to sign in. ### VS Code [Install in VS Code]() (opens VS Code) Or from a terminal: ```bash code --add-mcp '{"name":"bigquery","type":"http","url":"https://bigquery.googleapis.com/mcp"}' ``` Or commit it to the repo in `.vscode/mcp.json`: `.vscode/mcp.json`: ```json { "servers": { "bigquery": { "type": "http", "url": "https://bigquery.googleapis.com/mcp" } } } ``` VS Code asks you to sign in the first time the server starts. ### Devin Desktop 1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows): `mcp_config.json`: ```json { "mcpServers": { "bigquery": { "serverUrl": "https://bigquery.googleapis.com/mcp" } } } ``` 2. Refresh the MCP server list in Cascade and sign in when asked. Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers. ### Codex ```bash codex mcp add bigquery --url https://bigquery.googleapis.com/mcp codex mcp login bigquery ``` Or edit `~/.codex/config.toml` directly: `config.toml`: ```toml [mcp_servers.bigquery] url = "https://bigquery.googleapis.com/mcp" ``` ### Gemini CLI ```bash gemini mcp add --transport http bigquery https://bigquery.googleapis.com/mcp ``` Then, inside Gemini CLI, run `/mcp auth bigquery` to sign in. This adds it to the current project. Add `-s user` to use it everywhere. ### Any client Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file. ```json { "mcpServers": { "bigquery": { "type": "http", "url": "https://bigquery.googleapis.com/mcp" } } } ``` Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE. Client only starts local servers? Bridge it with `npx -y mcp-remote https://bigquery.googleapis.com/mcp`. ## Details - Server version: ESF - MCP protocol version: 2025-11-25 - Last checked: 2026-10-03 (reachable) - Listed: 2026-10-03 - Updated: 2026-10-03 --- Source: https://mcp.tc/i/bigquery (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report