How to integrate Google BigQuery MCP with OpenCode

Trusted by
AWS
Glean
Zoom
Airtable

30 min · no commitment · see it on your stack

Google BigQuery logo
OpenCode logo
divider

How to integrate Google BigQuery MCP with OpenCode

This guide explains how to connect Google BigQuery MCP to OpenCode using Composio Connect, which simplifies OAuth, API changes, and reliability concerns.

There are two ways to set this up:

Also integrate Google BigQuery with

Why use Composio?

Composio provides a single MCP server or CLI tool that exposes a set of meta-tools, allowing you to:

  • Connect to 1,000+ apps with on-demand tool loading, so you do not fill your LLM context window with unnecessary tool definitions.
  • Use programmatic tool calling through a remote Bash tool, letting LLMs write their own code to handle complex tool chaining. This reduces back-and-forth for frequent tool calls.
  • Handle large tool responses outside the LLM context to keep conversations lean.

Connect Google BigQuery with OpenCode

Option 1: Using Composio CLI

1. Install Composio CLI

Install the Composio CLI, authenticate, and initialize your project:

bash
# Install the Composio CLI
curl -fsSL https://composio.dev/install | bash

# Authenticate with Composio
composio login

During login, you will be redirected to the sign-in page. Finish the flow and you are all set.

Composio CLI authorization screen

2. Authorize Google BigQuery

Once the CLI is installed, it is essentially done. Give OpenCode access to your apps with these steps:

  1. Launch OpenCode.
  2. Prompt it to "Authenticate with Google BigQuery Composio".
  3. Complete the authentication and authorization flow, and your Google BigQuery integration is all set.
  4. Start asking anything you want.

Option 2: Using Composio MCP

You can also connect Google BigQuery to OpenCode by adding Composio as an MCP server through the OpenCode CLI.

1. Add the Composio MCP server

bash
opencode mcp add

This launches an interactive prompt.

2. Fill in the fields

FieldValue
Namecomposio
Typeremote
URLhttps://connect.composio.dev/mcp
Require OAuthYes
Have client IDNo
OpenCode MCP server interactive prompt for Composio

Alternatively, you can skip the interactive prompt and paste the configuration directly into your OpenCode config file.

Open your global OpenCode config:

bash
open ~/.config/opencode/opencode.json

Add this under the mcp key and save the file.

bash
{
  "mcp": {
    "composio": {
      "type": "remote",
      "url": "https://connect.composio.dev/mcp",
      "enabled": true
    }
  }
}

3. Authenticate

Authenticate the Composio MCP server you just added:

bash
opencode mcp auth composio

This opens a browser session. Authorize Composio and you are done.

Composio browser authorization for OpenCode MCP

4. Verify installation

bash
opencode mcp list

5. Connect Google BigQuery with OpenCode

Now, in the chat, ask the agent to connect to Google BigQuery or give it any Google BigQuery-related task.

For example, ask it to:

  • "Run yesterday's sales summary query"
  • "Find top 10 customers by revenue"
  • "Analyze traffic data for last quarter"

It will prompt you to authenticate and authorize access to Google BigQuery.

That is it. Composio tools are now available in OpenCode, and your Google BigQuery account is ready to use.

Supported Tools & Triggers

Tools
Cancel BigQuery JobTool to cancel a running BigQuery job.
Create Capacity CommitmentTool to create a new capacity commitment resource in BigQuery Reservation.
Create BigQuery ConnectionTool to create a new BigQuery connection to external data sources using the BigQuery Connection API.
Create Analytics Hub Data ExchangeTool to create a new Analytics Hub data exchange for sharing BigQuery datasets.
Create Analytics Hub ListingTool to create a new listing in a BigQuery Analytics Hub data exchange.
Create BigQuery DatasetTool to create a new BigQuery dataset with explicit location, labels, and description using the BigQuery Datasets API.
Create Analytics Hub ListingTool to create a new listing in a data exchange using Analytics Hub API.
Create BigQuery Data Policy (v2beta1)Tool to create a new data policy under a project with specified location using the v2beta1 BigQuery Data Policy API.
Create Analytics Hub Query TemplateTool to create a new query template in a BigQuery Analytics Hub Data Clean Room (DCR) data exchange.
Create BigQuery ReservationTool to create a new BigQuery reservation resource to guarantee compute capacity (slots) for query and pipeline jobs.
Create BigQuery Reservation AssignmentTool to create a BigQuery reservation assignment that allows a project, folder, or organization to submit jobs using slots from a specified reservation.
Create BigQuery RoutineTool to create a new user-defined routine (function or procedure) in a BigQuery dataset.
Create BigQuery TableTool to create a new, empty table in a BigQuery dataset.
Delete BigQuery DatasetTool to delete a BigQuery dataset specified by datasetId via the datasets.
Delete BigQuery Job MetadataTool to delete the metadata of a BigQuery job.
Delete BigQuery ML ModelTool to delete a BigQuery ML model from a dataset.
Delete BigQuery RoutineTool to delete a BigQuery routine by its ID.
Delete BigQuery TableTool to delete a BigQuery table from a dataset.
Get BigQuery ML ModelTool to retrieve a specific BigQuery ML model resource by model ID.
Get BigQuery Connection IAM PolicyTool to get the IAM access control policy for a BigQuery connection resource.
Get BigQuery Dataset MetadataTool to retrieve BigQuery dataset metadata including location via the datasets.
Get BigQuery JobTool to retrieve information about a specific BigQuery job.
Get BigQuery Query ResultsTool to get the results of a BigQuery query job via RPC.
Get BigQuery RoutineTool to retrieve a BigQuery routine (user-defined function or stored procedure) by its ID.
Get BigQuery Routine IAM PolicyTool to retrieve the IAM access control policy for a BigQuery routine resource.
Get BigQuery Service AccountTool to get the service account for a project used for interactions with Google Cloud KMS.
Get BigQuery Table IAM PolicyTool to retrieve the IAM access control policy for a BigQuery table resource.
Get BigQuery Table SchemaTool to fetch a BigQuery table's schema and metadata without querying row data.
Insert Data into BigQuery TableTool to stream data into BigQuery one record at a time without running a load job.
Insert BigQuery JobTool to start a new asynchronous BigQuery job (query, load, extract, or copy).
Insert BigQuery Job with UploadTool to start a new BigQuery load job with file upload.
List Analytics Hub ListingsTool to list all listings in a given Analytics Hub data exchange.
List BigQuery ConnectionsTool to list BigQuery connections in a given project and location.
List BigQuery Capacity CommitmentsTool to list all capacity commitments for the admin project.
List Data Exchange ListingsTool to list all listings in a given Analytics Hub data exchange using the v1beta1 API.
List BigQuery DatasetsTool to list datasets in a specific BigQuery project, including dataset locations.
List BigQuery JobsTool to list all jobs that you started in a BigQuery project.
List BigQuery Data Transfer LocationsTool to list information about supported locations for BigQuery Data Transfer Service.
List Connections in LocationTool to list BigQuery connections in a given project and location using the v1beta1 API.
List BigQuery Location Data PoliciesTool to list all data policies in a specified parent project and location using the v2beta1 API.
List BigQuery ModelsTool to list all BigQuery ML models in a specified dataset.
List Organization Data ExchangesTool to list all data exchanges from projects in a given organization and location using Analytics Hub API.
List BigQuery ProjectsTool to list BigQuery projects to which the user has been granted any project role.
List Analytics Hub Query TemplatesTool to list all query templates in a given Analytics Hub data exchange.
List BigQuery Reservation AssignmentsTool to list BigQuery reservation assignments.
List BigQuery Reservation GroupsTool to list all BigQuery reservation groups for a project in a specified location.
List BigQuery ReservationsTool to list all BigQuery reservations for a project in a specified location.
List BigQuery RoutinesTool to list all routines (user-defined functions and stored procedures) in a BigQuery dataset.
List BigQuery Row Access PoliciesTool to list all row access policies on a specified BigQuery table.
List BigQuery Table DataTool to list the content of a BigQuery table in rows via the REST API.
List BigQuery TablesTool to list tables in a BigQuery dataset via the REST API.
Patch BigQuery DatasetTool to update an existing BigQuery dataset using RFC5789 PATCH semantics.
Patch BigQuery ML ModelTool to update specific fields in an existing BigQuery ML model using PATCH semantics.
Patch BigQuery TableTool to update specific fields in an existing BigQuery table using RFC5789 PATCH semantics.
QueryQuery Tool runs a SQL query in BigQuery using the REST API.
Search All BigQuery Reservation AssignmentsTool to search all BigQuery reservation assignments for a specified resource in a particular region.
Set BigQuery Routine IAM PolicyTool to set the IAM access control policy for a BigQuery routine resource.
Test BigQuery Routine IAM PermissionsTool to test which IAM permissions the caller has on a BigQuery routine.
Undelete BigQuery DatasetTool to undelete a BigQuery dataset within the time travel window.
Update BigQuery ConnectionTool to update a specified BigQuery connection using the BigQuery Connection API.
Update BigQuery DatasetTool to update information in an existing BigQuery dataset using the PUT method.
Update BigQuery RoutineTool to update an existing BigQuery routine (function or stored procedure).
Update BigQuery TableTool to update an existing BigQuery table.

Way Forward

Now that Google BigQuery is connected, extend your setup by connecting the other apps you already use every day, so your agent can run true cross-app workflows end to end.

  • Connect Calendar to turn threads into scheduled meetings automatically.
  • Connect Slack or Teams to post summaries, approvals, and alerts where your team works.
  • Connect Notion, Linear, Jira, or Asana to convert requests into tickets, tasks, and docs.
  • Connect Drive, Dropbox, or OneDrive to fetch, file, and share attachments without manual steps.

Start with one workflow you do repeatedly, then keep adding apps as you find new handoffs. With everything behind a single MCP endpoint, your agent can coordinate multiple tools safely and reliably in one conversation.

How to build Google BigQuery MCP Agent with another framework

FAQ

What are the differences in Tool Router MCP and Google BigQuery MCP?

With a standalone Google BigQuery MCP server, the agents and LLMs can only access a fixed set of Google BigQuery tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Google BigQuery and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with OpenCode?

Yes, you can. OpenCode fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Google BigQuery tools.

Can I manage the permissions and scopes for Google BigQuery while using Tool Router?

Yes, absolutely. You can configure which Google BigQuery scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Google BigQuery data and credentials are handled as safely as possible.

Used by agents from

Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.