{
  "name": "io.github.LucasHild/mcp-server-bigquery",
  "description": "A community-maintained MCP that connects an AI agent to Google BigQuery. Inspect datasets, list tables, describe schemas, and run dry-run + live SQL against your warehouse. Authentication uses standard Application Default Credentials, so it inherits whatever your gcloud session is already authorised for.",
  "status": "active",
  "version": "latest",
  "_meta": {
    "com.top-mcps/lastVerified": "2026-05-27",
    "com.top-mcps/score": {
      "value": 70,
      "rubricVersion": "2026-04",
      "lastComputed": "2026-06-02T13:16:41.643Z",
      "methodology": "https://top-mcps.com/about/methodology"
    },
    "com.top-mcps/stats": {
      "fetchedAt": "2026-06-02T11:55:52.278Z",
      "githubStars": 126,
      "lastCommitAt": "2026-03-26T13:57:09Z"
    }
  },
  "repository": {
    "url": "https://github.com/LucasHild/mcp-server-bigquery",
    "source": "github"
  },
  "author": {
    "name": "Community"
  },
  "packages": [
    {
      "registryType": "pypi",
      "registryBaseUrl": "https://pypi.org",
      "identifier": "mcp-server-bigquery",
      "version": "latest",
      "transport": {
        "type": "stdio"
      },
      "environmentVariables": [
        {
          "name": "GOOGLE_CLOUD_PROJECT",
          "description": "GOOGLE_CLOUD_PROJECT — required credential for BigQuery.",
          "isRequired": true,
          "isSecret": true
        },
        {
          "name": "GOOGLE_APPLICATION_CREDENTIALS",
          "description": "GOOGLE_APPLICATION_CREDENTIALS — required credential for BigQuery.",
          "isRequired": true,
          "isSecret": true
        }
      ]
    }
  ],
  "capabilities": {
    "tools": [
      {
        "name": "list_datasets",
        "description": "List BigQuery datasets in the active project.",
        "sideEffect": "read"
      },
      {
        "name": "list_tables",
        "description": "List tables in a dataset.",
        "sideEffect": "read",
        "args": [
          {
            "name": "dataset",
            "type": "string",
            "required": true
          }
        ]
      },
      {
        "name": "describe_table",
        "description": "Return schema + size estimates for a table.",
        "sideEffect": "read",
        "args": [
          {
            "name": "table",
            "type": "string",
            "required": true
          }
        ]
      },
      {
        "name": "dry_run_query",
        "description": "Return bytes-processed + cost estimate without executing.",
        "sideEffect": "read",
        "args": [
          {
            "name": "sql",
            "type": "string",
            "required": true
          }
        ]
      },
      {
        "name": "query",
        "description": "Execute a SELECT and return rows.",
        "sideEffect": "read",
        "args": [
          {
            "name": "sql",
            "type": "string",
            "required": true
          }
        ]
      }
    ],
    "security": {
      "scope": "read-only",
      "sandbox": "Authenticates via Google ADC — inherits the active gcloud identity or a service-account key in env. Read-only by default; DML must be explicitly enabled. Combine with IAM roles scoped to the smallest dataset and the smallest project that satisfies the workflow.",
      "gotchas": [
        "BigQuery is billed per byte scanned — always dry_run new SQL before running it.",
        "Service-account keys in env vars persist in client config files. Prefer ADC + short-lived gcloud login.",
        "Read-only is MCP-side, not IAM. Use a viewer-role service account as defence in depth."
      ]
    }
  },
  "_links": {
    "html": "https://top-mcps.com/mcp/bigquery",
    "markdown": "https://top-mcps.com/mcp/bigquery.md",
    "methodology": "https://top-mcps.com/about/methodology"
  }
}