How to Use the Google Sheets MCP in Google ADK

Q: Can my Google ADK agent create brand new Google Sheets files?

Yes, your Google ADK agent calls createspreadsheet to generate a new Google Sheets file. Once created, your Google ADK agent receives the spreadsheet ID and can start writing data.

Q: How do I clear specific ranges using Google ADK?

Your Google ADK agent invokes clearsheetvalues with the exact Google Sheets range coordinates. This wipes the cell values instantly while leaving your Google Sheets formulas and structures intact.

Connect your Google ADK pipelines to Google Sheets to write structured summaries directly from Gemini's long-context runs.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Google Sheets MCP to Google ADK

Create your Vinkius account to connect Google Sheets to Google ADK 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 Sheets with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map Gemini context directly to Google Sheets

The `append_sheet_values` tool writes rows of text or numbers directly to the end of a Google Sheets document after your Google ADK agent parses a large dataset. Because Gemini handles massive token contexts, this tool lets your Google ADK agent dump extracted insights directly into a Google Sheets tab without manual copy-pasting. Your Google ADK agent uses `get_sheet_values` to pull existing Google Sheets rows into Gemini's context window first. This lets the Google ADK agent check for duplicates before calling the append tool, ensuring your Google Sheets files stay clean.

Manage multiple sheets with Google ADK agents

The `add_sheet` tool creates a new tab inside your Google Sheets file whenever your Google ADK agent needs to isolate a new batch of processed data. This prevents your Google ADK agent from cluttering your main Google Sheets dashboard during multi-step runs. If a run fails or a tab becomes obsolete, the Google ADK agent executes `delete_sheet` to remove the temporary Google Sheets workspace. By using this MCP Server, your Google ADK pipelines can manage the entire lifecycle of your Google Sheets documents programmatically.

Read and write bulk spreadsheet data efficiently

The `batch_get_values` tool retrieves data from multiple cell ranges simultaneously, allowing your Google ADK agent to analyze disparate Google Sheets sections in one go. This reduces Google Sheets API call overhead and keeps your Gemini-powered Google ADK agent runs fast and responsive. When it's time to write back, the Google ADK agent uses `update_sheet_values` to modify specific Google Sheets cell coordinates with its final reasoning outputs. This direct writing method via our MCP Server ensures your Google ADK agent's conclusions are immediately visible in your Google Sheets tables.

Setup guide

Set up Google Sheets MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Google Sheets tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Google Sheets_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Google Sheets tools via MCP.",
    tools=mcp_tools,
)

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 Sheets. 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 Sheets 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 Sheets MCP in Google ADK

The MCP Server passes Google Sheets rate limit errors directly back to the Google ADK runner. You can handle these errors in Python by implementing standard backoff strategies in your Google ADK execution loop.

Yes, your Google ADK agent calls `create_spreadsheet` to generate a new Google Sheets file. Once created, your Google ADK agent receives the spreadsheet ID and can start writing data.

Yes, the server manages authentication using your configured Google service account. This allows your Google ADK agent to access target Google Sheets files securely without forcing human users to log in.

Your Google ADK agent invokes `clear_sheet_values` with the exact Google Sheets range coordinates. This wipes the cell values instantly while leaving your Google Sheets formulas and structures intact.

Your Google Sheets cell values and metadata are transmitted through an isolated, zero-trust V8 sandbox on Vinkius. We do not store or log your Google Sheets content, keeping your Google ADK enterprise data strictly private.

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