How to Use the Retable MCP in Google ADK

Q: Can I limit which Retable tools my Google ADK agent can access?

Yes. You can pass a toolnames filter to the toolset configuration. This lets you restrict the agent to read-only tools like listrecords while blocking destructive tools like deleterecord.

Feed your Google ADK enterprise agents live Retable spreadsheet data to run deep reasoning loops alongside BigQuery.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Retable MCP to Google ADK

Create your Vinkius account to connect Retable to Google ADK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Retable with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Direct Spreadsheet Queries

The `list_records` tool pulls raw rows from your active tables so Gemini can process them in its long-context window. For targeted lookups, the agent uses `get_record` to isolate a single row's values. This direct access eliminates the need to export CSVs or write custom ETL pipelines. Your agent acts directly on live relational data via MCP, combining spreadsheet context with your enterprise Google Cloud resources.

Map out Retable project structures dynamically

The `list_projects` tool queries your workspace to find active databases. Once the agent locates the correct workspace, it runs `list_tables` to find the specific sheet it needs to update or read. This discovery process relies on `get_project` and `get_table` to pull metadata. Your agent maps the relational layout of your spreadsheets on its own, making the MCP Server highly adaptable to workspace changes.

Write and modify records using this MCP Server

The `create_record` tool appends new data points to your tables instantly. If your agent detects that a row contains outdated information, it calls `update_record` to modify only the target fields. When cleanup is necessary, the agent uses `delete_record` to remove obsolete entries. Before starting any of these database operations, the agent runs `check_retable_status` to confirm the API connection is active.

Setup guide

Set up Retable 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 Retable 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="Retable_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Retable 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 Retable. 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 Retable 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 Retable MCP in Google ADK

Instantiate McpToolset with your Vinkius HTTP URL and pass it to your LlmAgent tools list. The Gemini model automatically registers the tools and decides when to call them based on user prompts.

Yes. You can pass a tool_names filter to the toolset configuration. This lets you restrict the agent to read-only tools like `list_records` while blocking destructive tools like `delete_record`.

Gemini's million-token context window easily handles large payloads returned by `list_records`. However, for massive sheets, it is best to query specific rows using `get_record` to keep execution fast.

No. Vinkius hosts the MCP Server in a managed cloud sandbox. Your cloud-hosted Google ADK agent connects directly to the secure Vinkius endpoint without any local infrastructure.

Your Retable project configurations and table records travel through an ephemeral, zero-trust connection. No data is cached or stored by Vinkius, keeping your enterprise spreadsheet records isolated and secure.

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