Integrate OpenCode with Live BigQuery Data via CData Connect AI
OpenCode is an open source AI coding agent that connects to a wide range of LLM providers. It supports the model context protocol (MCP), allowing you to configure local or remote MCP servers in its configuration files to add external tools and data sources and give the agent access to live data.
By integrating OpenCode with CData Connect AI through the built-in MCP Server, OpenCode gains governed, real-time access to live BigQuery data. You can list catalogs, explore schemas, and query records from BigQuery data using natural language prompts, with all data access running securely against authorized sources.
This article explains how to configure BigQuery connectivity in Connect AI, generate the required personal access token, install OpenCode, add the Connect AI MCP Server in the project configuration file, configure an LLM provider, and verify the integration by querying live BigQuery data from OpenCode.
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 OpenCode
Connectivity to BigQuery from OpenCode is made possible through Connect AI's Remote MCP Server. To interact with BigQuery data from OpenCode, start by creating and configuring a BigQuery connection in Connect AI.
- Log into Connect AI, click Sources, and then click Add Connection
- Select BigQuery from the Add Connection panel
-
BigQuery uses OAuth to authenticate. Click Sign in to authenticate with BigQuery
- Navigate to the Permissions tab and update user-based permissions
Add a Personal Access Token
A Personal Access Token (PAT) is used to authenticate the connection to Connect AI from OpenCode. It is best practice to create a separate PAT for each integration to maintain granular access control.
- Click the gear icon () at the top right of the Connect AI app to open Settings
- On the Settings page, go to the Access Tokens section and click Create PAT
- Give the PAT a descriptive name and click Create
- Copy the token when displayed and store it securely. It will not be shown again
With the BigQuery connection configured and a PAT generated, OpenCode can now connect to BigQuery data through Connect AI.
Step 2: Install OpenCode and configure the Connect AI MCP Server
Next, install OpenCode, add the Connect AI Remote MCP Server in your project configuration file, and configure an LLM provider so the agent can discover and call live data tools through Connect AI.
- Download and install OpenCode by following the official installation guide
- Create a new folder for your project, or open an existing project directory
-
In the root of that directory, create a file named opencode.json and paste the following configuration:
{ "$schema": "https://opencode.ai/config.json", "mcp": { "cdata-connect-ai": { "type": "remote", "url": "https://mcp.cloud.cdata.com/mcp", "enabled": true, "oauth": false, "headers": { "Authorization": "Basic your_base64_encoded_email_PAT" }, "timeout": 30000 } } }Note: OpenCode will use Basic authentication with Connect AI. Combine your Connect AI user email and the PAT you created earlier in the format email:PAT, base64 encode the combined string, and prefix it with Basic. For example, given [email protected]:ABC123...XYZ789, the Authorization header value becomes something like: Basic dXNlckBkb21haW4uY29tOkFCQzEyMy4uLlhZWjc4OQ==
-
Open the project directory in OpenCode. Select the project from the project dropdown, or click Add project to point OpenCode at the folder that contains opencode.json
-
Configure an LLM provider so the agent can interpret prompts and call MCP tools. Open the model selector (Ctrl + '), choose a provider such as OpenAI, Anthropic, or Google, and enter your API key
With the MCP server added in opencode.json and an LLM provider configured, OpenCode is ready to query live BigQuery data through Connect AI.
Step 3: Query live BigQuery data from OpenCode
With the integration complete, use OpenCode to interact with live BigQuery data through natural language prompts handled by the configured LLM.
-
In a new session, type a prompt in the chat input, for example:
- Use the cdata-connect-ai tools to list all available catalogs
- Show the available schemas and tables for BigQuery
- Query the top 5 records from a table in BigQuery
-
OpenCode calls the Connect AI MCP Server and returns live results from BigQuery data
At this point, OpenCode communicates with the Connect AI MCP Server and retrieves live BigQuery data through remote MCP tools directly from your AI coding agent.
Get CData Connect AI
To access hundreds of SaaS, big data, and NoSQL sources directly from your cloud applications, try CData Connect AI today. Download a free 14-day trial of CData Connect AI, and our Support Team is available to help with any questions you have.