Skip to main content

Announcing StackOne Defender: leading open-source prompt injection guard for your agent • Read More →

Connect

Connectors Agent Auth MCP Connector Builder

Optimize

Tool Discovery Falcon Engine

Secure

Defender
Connectors

HRIS / HCM

Employee Onboarding Employee Offboarding

Recruiting

Application Screening Interview Scheduling

Customer Support

Ticket Triage Voice Call Summarization

Sales & CRM

Deal Risk Scoring Lead Qualification

Accounting & Finance

Invoice Processing Month-End Accruals

Marketing

Campaign Reports Lead Nurture Sequences
View all use cases

Developers

Docs Changelog Status

Learn

Blog Case Studies Events Partners
Pricing
Login Book Demo Start Free

Google BigQuery MCP Server
for AI Agents

Production-ready Google BigQuery MCP server with 34 extensible actions — plus built-in authentication, security, and optimized execution.

Start Free Book Demo Read Docs →
Google BigQuery logo
Google BigQuery MCP Server
Built by StackOne StackOne

Coverage

34 Agent Actions

Create, read, update, and delete across Google BigQuery — and extend your agent's capabilities with custom actions.

MCP Actions → Create Actions →

Authentication

Agent Tool Authentication

Per-user OAuth in one call. Your Google BigQuery MCP server gets session-scoped tokens with zero credentials stored on your infra.

Agent Auth →

Security

Agent Protection

Every Google BigQuery tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.

Prompt Injection Defense →

Performance

Max Agent Context. Min Cost.

Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Google BigQuery call.

Tools Discovery →

What is the Google BigQuery MCP Server?

A Google BigQuery MCP server lets AI agents read and write Google BigQuery data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Google BigQuery MCP server ships with 34 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, and optimized agent context. Connect it from MCP clients like Claude Desktop, Cursor, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.

All Google BigQuery MCP Tools and Actions

Every action from Google BigQuery's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.

Datasets

  • Create Dataset

    Creates a new empty dataset

  • List Datasets

    Lists all datasets in the specified project

  • Get Dataset

    Returns the dataset specified by datasetID

  • Update Dataset

    Updates information in an existing dataset

  • Delete Dataset

    Deletes the dataset specified by datasetId

Table IAM Policys

  • Get Table IAM Policy

    Gets the IAM policy for the specified table

  • Set Table IAM Policy

    Sets the IAM policy for the specified table

Jobs

  • List Jobs

    Lists all jobs in the specified project

  • Get Job

    Returns information about a specific job

  • Delete Job

    Requests the deletion of the metadata of a job

Models

  • List Models

    Lists all models in the specified dataset

  • Get Model

    Gets the specified model resource

  • Update Model

    Updates information in an existing model

  • Delete Model

    Deletes the model specified by modelId

Routines

  • Create Routine

    Creates a new routine in the dataset

  • List Routines

    Lists all routines in the specified dataset

  • Get Routine

    Gets the specified routine resource

  • Update Routine

    Updates information in an existing routine

  • Delete Routine

    Deletes the routine specified by routineId

Tables

  • Create Table

    Creates a new, empty table in the dataset

  • List Tables

    Lists all tables in the specified dataset

  • Get Table

    Gets the specified table resource

  • Update Table

    Updates information in an existing table

  • Delete Table

    Deletes the table specified by tableId

Other (10)

  • Get Query Results

    Retrieves the results of a query job

  • List Projects

    Lists all projects to which the user has been granted any project role

  • Get Service Account

    Returns the email address of the service account for the project

  • List Table Data

    Lists the content of a table in rows

  • Undelete Dataset

    Undeletes a dataset which is within time travel window

  • Test Table IAM Permissions

    Tests if the caller has the specified permissions on a table

  • Run Query (Synchronous)

    Runs a BigQuery SQL query synchronously and returns query results

  • Insert Job (Asynchronous)

    Starts a new asynchronous job (query, load, extract, copy)

  • Cancel Job

    Requests that a job be cancelled

  • Insert Table Data

    Streams data into BigQuery using the streaming insert API; supports inserting one or more rows per request

Set Up Your Google BigQuery MCP Server in Minutes

One endpoint. Any framework. Your agent is talking to Google BigQuery in under 10 lines of code.

MCP Clients

Agent Frameworks

Claude Desktop
{
  "mcpServers": {
    "stackone": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://api.stackone.com/mcp?x-account-id=<account_id>",
        "--header",
        "Authorization: Basic <YOUR_BASE64_TOKEN>"
      ]
    }
  }
}

More Data Infrastructure MCP Servers

Supabase

128+ actions

Grafana

89+ actions

Render

81+ actions

Snowflake

80+ actions

Sentry

74+ actions

Honeycomb

68+ actions

Talend

52+ actions

All Data Infrastructure MCP Servers →

Google BigQuery MCP Server Resources

MCP Code Mode: Keeping Tool Responses Out of Agent Context

Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.

11 min

Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery

Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.

10 min

Indirect Prompt Injection Defense for MCP Tools: A Technical Guide

MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.

12 min

Google BigQuery MCP Server FAQ

Google BigQuery MCP server vs direct API integration — what's the difference?
A Google BigQuery MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Google BigQuery. A Google BigQuery MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Google BigQuery at runtime. StackOne provides both.
How does Google BigQuery authentication work for AI agents?
Google BigQuery authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Google BigQuery account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.
Are Google BigQuery MCP tools vulnerable to prompt injection?
Yes — Google BigQuery MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a Google BigQuery agent and how do I avoid it?
Context bloat happens when Google BigQuery tool schemas and API responses eat your Google BigQuery agent's memory, preventing it from reasoning effectively. A single Google BigQuery query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my Google BigQuery agent can access?
Yes — you can limit which actions your Google BigQuery agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my Google BigQuery MCP server?
Yes — you can create custom agent actions for your Google BigQuery MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Google BigQuery's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Google BigQuery MCP server?
Skip a Google BigQuery MCP server if your integration is purely software-to-software — direct Google BigQuery API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Google BigQuery actions at runtime.
What AI frameworks and AI clients does the StackOne Google BigQuery MCP server support?
The StackOne Google BigQuery MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.

Put your AI agents to work

All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.

Start Free Book Demo