mcp-registry/mcp-bigquery-server

    ==================
      
       /// MCP ///
      /// MCP ///
        
    ==================
        
    [server:online]
    [protocol:ready]

mcp-bigquery-server

by ergut

A Model Context Protocol (MCP) server that provides secure, read-only access to Google BigQuery so LLMs can run natural-language queries against your data.

101
26
Open Source
GitHubDocumentationNPM

Installation

1. Prerequisites
• Node.js ≥ 18
• A Google Cloud project that has BigQuery enabled
• A BigQuery service-account JSON key with at least bigquery.jobs.create and bigquery.tables.getData permissions on the datasets you wish to expose.
2. Acquire credentials
export GOOGLE_APPLICATION_CREDENTIALS=/absolute/path/to/key.json
3. Install the server
git clone https://github.com/ergut/mcp-bigquery-server.git cd mcp-bigquery-server npm install --production (or install globally from NPM) npm install -g mcp-bigquery-server
4. Configure allowed datasets and server options
Create a config file (config.json): { "projectId": "your-gcp-project", "allowedDatasets": ["project.dataset1", "project.dataset2"], "port": 8080, "auth": { "mode": "bearer", "tokens": ["<YOUR_API_TOKEN>"] } }
5. Start the MCP server
npx mcp-bigquery-server --config ./config.json # or, if installed globally mcp-bigquery-server --config ./config.json
6. Verify
curl http://localhost:8080/health → {"status":"ok"} The server is now ready to service MCP requests from LLM tooling.

Documentation

License: MIT License
Updated 7/15/2025