How to Use the Google BigQuery MCP in LangChain

Q: How do I run SQL queries using Google BigQuery and LangChain?

You register the executequery tool with your LangChain agent. The agent can then write and run standard SQL queries directly against your warehouse, returning raw rows as text to feed the next step in your chain.

Q: Can LangChain agents discover table structures dynamically?

Yes, the agent calls listtables to see what is available in a dataset. Then, it uses gettable to pull the exact column names and types so it can construct valid SQL queries.

Q: How does Google BigQuery handle long-running queries inside LangChain?

Long queries run asynchronously in GCP. Your agent uses getjob to poll the status of the query, preventing your LangChain execution from timing out while waiting for massive datasets to process.

Run massive SQL queries and inspect schemas directly inside your LangChain pipelines without writing boilerplate connector code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Google BigQuery MCP to LangChain

Create your Vinkius account to connect Google BigQuery to LangChain and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Google BigQuery with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Schema-First SQL Execution

The `get_table` tool retrieves the exact schema of your BigQuery target table before your agent writes a single line of SQL. This MCP Server setup prevents your pipeline from executing broken queries that waste your Google Cloud budget on syntax errors. Once the schema is verified, the agent uses `execute_query` to pull the actual data. This two-step chain keeps your LangChain runs clean, predictable, and cheap.

Trace BigQuery Jobs in LangSmith

The `get_job` tool pulls the exact status and resource usage of any active query run. LangChain developers can map this tool directly into their custom chains to monitor heavy analytical workloads. Your agent uses `list_jobs` to track run histories and catch stuck processes. You get full observability over your database operations right inside your LangSmith dashboard.

Multi-Server LangChain MCP Server Integration

The `list_datasets` tool exposes all available datasets within your active GCP project to your agent. This MCP Server lets your conversational chains discover tables dynamically without hardcoded environment variables. After locating the right dataset, the agent runs `list_tables` to map out the structure of your warehouse. This allows your multi-step chains to pivot their strategy based on the data they find.

Setup guide

Set up Google BigQuery MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Google BigQuery tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "google-bigquery-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Google BigQuery transactions"
    })
    print(result["messages"][-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Google BigQuery. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Google BigQuery now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Google BigQuery MCP in LangChain

You register the `execute_query` tool with your LangChain agent. The agent can then write and run standard SQL queries directly against your warehouse, returning raw rows as text to feed the next step in your chain.

Yes, the agent calls `list_tables` to see what is available in a dataset. Then, it uses `get_table` to pull the exact column names and types so it can construct valid SQL queries.

Long queries run asynchronously in GCP. Your agent uses `get_job` to poll the status of the query, preventing your LangChain execution from timing out while waiting for massive datasets to process.

No, Vinkius handles the OAuth and service account authentication. Your application only needs a single endpoint token to access the MCP Server, keeping your local environment clean.

Your SQL queries and schema metadata never touch third-party servers. All requests run in an isolated V8 sandbox that destroys itself immediately after the tool execution completes.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript