How to Connect to Live BigQuery Data in n8n Workflows and Agents (via CData Connect AI)

Yazhini G
Yazhini G
Technical Marketing Engineer
Leverage the CData Connect AI Remote MCP Server to enable n8n to securely read and take actions on your BigQuery data for you.

n8n is an open-source workflow automation tool that allows you to connect various applications and services to automate tasks and processes. When combined with CData Connect AI Remote MCP, you can leverage n8n to interact with your BigQuery data in real-time. This article outlines the process of connecting to BigQuery using Connect AI Remote MCP and creating a basic workflow in n8n to interact with your BigQuery data.

CData Connect AI offers a dedicated cloud-to-cloud interface for connecting to BigQuery data. The CData Connect AI Remote MCP Server enables secure communication between n8n and BigQuery. This allows you to ask questions and take actions on your BigQuery data using n8n, all without the need for data replication to a natively supported database. With its inherent optimized data processing capabilities, CData Connect AI efficiently channels all supported SQL operations, including filters and JOINs, directly to BigQuery. This leverages server-side processing to swiftly deliver the requested BigQuery data.

In this article, we show how to build a simple chat agent in n8n to conversational explore (or Vibe Query) your data. The connectivity principals apply to any n8n workflow. With Connect AI you can build workflows and agents with access to live BigQuery data, plus hundreds of other sources.

About BigQuery Data Integration

CData simplifies access and integration of live Google BigQuery data. Our customers leverage CData connectivity to:

  • Simplify access to BigQuery with broad out-of-the-box support for authentication schemes, including OAuth, OAuth JWT, and GCP Instance.
  • Enhance data workflows with Bi-directional data access between BigQuery and other applications.
  • Perform key BigQuery actions like starting, retrieving, and canceling jobs; deleting tables; or insert job loads through SQL stored procedures.

Most CData customers are using Google BigQuery as their data warehouse and so use CData solutions to migrate business data from separate sources into BigQuery for comprehensive analytics. Other customers use our connectivity to analyze and report on their Google BigQuery data, with many customers using both solutions.

For more details on how CData enhances your Google BigQuery experience, check out our blog post: https://www.cdata.com/blog/what-is-bigquery


Getting Started


Step 1: Configure BigQuery Connectivity for n8n

Connectivity to BigQuery from n8n is made possible through CData Connect AI Remote MCP. To interact with BigQuery data from n8n, we start by creating and configuring a BigQuery connection in CData Connect AI.

  1. Log into Connect AI, click Sources, and then click Add Connection
  2. Select "BigQuery" from the Add Connection panel
  3. BigQuery uses OAuth to authenticate. Click "Sign in" to authenticate with BigQuery.
  4. Navigate to the Permissions tab in the Add BigQuery Connection page and update the User-based permissions.

Add a Personal Access Token

A Personal Access Token (PAT) is used to authenticate the connection to Connect AI from n8n. It is best practice to create a separate PAT for each service to maintain granularity of access.

  1. Click on the Gear icon () at the top right of the Connect AI app to open the settings page.
  2. On the Settings page, go to the Access Tokens section and click Create PAT.
  3. Give the PAT a name and click Create.
  4. The personal access token is only visible at creation, so be sure to copy it and store it securely for future use.

With the connection configured and a PAT generated, we are ready to connect to BigQuery data from n8n.

Step 2: Connect n8n to CData Connect AI

Follow these steps to connect to CData Connect AI in n8n:

  1. Sign in to n8n.io or create a new account.
  2. Create a Workflow in n8n that uses the MCP Client tool. The example Workflow below acts as a chatbot. OpenAI was used as the Chat Model, and Simple Memory was used for the Memory.
  3. Configure the MCP Client node in the Workflow:
    • Set Endpoint to https://mcp.cloud.cdata.com/mcp (found in the "Connect Data to AI" ribbon in Connect AI)
    • Set Server Transport to HTTP Streamable
    • Set Authentication to Header Auth and set the following properties to use Basic authentication:
      • Set Name to Authorization
      • Set Value to Basic EMAIL:PAT, replacing the EMAIL and PAT with your Connect AI email address and the PAT created previously. For example: Basic [email protected]:Uu90pt5vEO..."

Optional Step: Give the AI Agent context

This step establishes the AI Agent's role and provides context for the conversation through the System Message parameter in the AI Agent node. By providing a system message that explicitly informs the agent about its role as an MCP Server expert and lists the available tools, you can enhance the agent's understanding and response accuracy. For example, you can set the System Message to: 

You are an expert at using the MCP Client tool connected which is the CData Connect AI MCP Server. Always search thoroughly and use the most relevant MCP Client tool for each query. Below are the available tools and a description of each:
queryData: Execute SQL queries against connected data sources and retrieve results. When you use the queryData tool, ensure you use the following format for the table name: catalog.schema.tableName
getCatalogs: Retrieve a list of available connections from CData Connect AI. The connection names should be used as catalog names in other tools and in any queries to CData Connect AI. Use the `getSchemas` tool to get a list of available schemas for a specific catalog.
getSchemas: Retrieve a list of available database schemas from CData Connect AI for a specific catalog. Use the `getTables` tool to get a list of available tables for a specific catalog and schema.
getTables: Retrieve a list of available database tables from CData Connect AI for a specific catalog and schema. Use the `getColumns` tool to get a list of available columns for a specific table.
getColumns: Retrieve a list of available database columns from CData Connect AI for a specific catalog, schema, and table.
getProcedures: Retrieve a list of stored procedures from CData Connect AI for a specific catalog and schema
getProcedureParameters: Retrieve a list of stored procedure parameters from CData Connect AI for a specific catalog, schema, and procedure.
executeProcedure: Execute stored procedures with parameters against connected data sources

Step 3: Explore Live BigQuery Data with n8n

With the Workflow created in n8n and the MCP Client connected, you can now interact with your BigQuery data using n8n. The MCP Client node allows you to send queries and receive responses from the BigQuery data source in real-time.

Open the Workflow in n8n and execute it to start interacting with your BigQuery data. You can ask questions, retrieve data, and perform actions on your BigQuery data using the MCP Client node:

Get CData Connect AI

To get live data access to 300+ SaaS, Big Data, and NoSQL sources directly from your cloud applications, try CData Connect AI today!

Ready to get started?

Learn more about CData Connect AI or sign up for free trial access:

Free Trial

In this article

Related articles