How to Use the Kintone MCP in Google ADK

Q: How do I install the Google ADK toolset for Kintone?

Run pip install google-adk and import McpToolset to load the MCP server. Configure it with StreamableHttpServerParameters pointing to your Vinkius endpoint, then pass the toolset directly to your LlmAgent.

Q: Can Gemini write new records to Kintone using Google ADK?

Yes, Gemini can create entries directly. The agent uses addrecord with a structured JSON payload containing the field values, allowing it to log customer inquiries or inventory updates automatically.

Q: How does this Kintone MCP Server handle complex layout structures?

The agent calls getapplayout to retrieve the visual layout and grid positioning of the form. This allows your Google ADK agent to understand how fields are grouped on the screen before editing them.

Q: How is my Kintone space membership data protected?

All requests to listspacemembers are encrypted in transit. Vinkius executes each tool call in a zero-trust, ephemeral sandbox, ensuring your user directories and membership rosters are never written to persistent disk.

Connect Gemini to your Kintone apps and run high-volume data analysis using the Google ADK and MCP.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kintone MCP to Google ADK

Create your Vinkius account to connect Kintone 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 Kintone with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed Kintone data into Gemini long-context windows

The Google ADK lets Gemini digest massive Kintone datasets by taking advantage of its million-token context. Your agent can pull hundreds of rows using `list_records` and analyze business trends without running out of memory. Instead of processing data in tiny chunks, the Gemini agent reads entire Kintone tables at once. It uses `get_app_details` to understand the app context, then processes the full dataset to find bottlenecks in your workflows.

Run BigQuery workflows with this Kintone MCP Server

Connect your enterprise data warehouse directly to your Kintone apps with this MCP Server. Your Gemini agent can query historical sales data in BigQuery, match it against active files retrieved via `list_records`, and update status fields instantly. The Gemini agent coordinates these systems by checking schemas first. It calls `list_form_fields` to find the correct target fields, then executes `update_record` to keep your Kintone CRM and BigQuery tables synchronized.

Manage space membership via Google Cloud agents

Automate team onboarding inside your Kintone workspace. Your Google ADK agent can check who has access to specific project spaces by calling `list_space_members` and compare it against your internal Google Cloud directory. This helps you keep permissions updated without manual audits on Kintone. If the Google ADK agent detects a discrepancy, it flags the missing team members, ensuring your Kintone collaboration spaces remain secure.

Setup guide

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

Run `pip install google-adk` and import `McpToolset` to load the MCP server. Configure it with `StreamableHttpServerParameters` pointing to your Vinkius endpoint, then pass the toolset directly to your `LlmAgent`.

Yes, Gemini can create entries directly. The agent uses `add_record` with a structured JSON payload containing the field values, allowing it to log customer inquiries or inventory updates automatically.

The agent calls `get_app_layout` to retrieve the visual layout and grid positioning of the form. This allows your Google ADK agent to understand how fields are grouped on the screen before editing them.

Yes, you can use the optional tool names filter in the SDK. If you only want the agent to read data, you can expose `list_records` and `get_record` while blocking write operations.

All requests to `list_space_members` are encrypted in transit. Vinkius executes each tool call in a zero-trust, ephemeral sandbox, ensuring your user directories and membership rosters are never written to persistent disk.

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