How to Use the Kintone MCP in OpenAI Agents SDK

Q: How do I connect the OpenAI Agents SDK to Kintone?

Install the package using pip install openai-agents and initialize the MCP server. Pass the Vinkius URL to MCPServerStreamableHttpParams and load it into your agent constructor using the mcpservers list.

Q: How do I handle form field validation with this Kintone MCP Server?

Have your agent call listformfields before attempting to write data. This lets the agent inspect the required field codes and validation rules, ensuring the payload for addrecord matches your app schema.

Run secure agents that manage Kintone records and workspaces using the OpenAI Agents SDK 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 OpenAI Agents SDK

Create your Vinkius account to connect Kintone to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trace Kintone record edits in OpenAI

Your OpenAI Agents SDK workflow can now write directly to Kintone apps. By using `add_record` and `update_record`, your agents update customer files and inventory logs while you watch the execution steps live on the OpenAI dashboard. This integration logs every tool call, so you know exactly when an agent attempts to modify data. If an agent tries to purge old logs with `delete_records`, the OpenAI dashboard records the payload and the exact parameters passed, giving you a clear audit trail.

Safe handoffs for Kintone app inspection

Build a multi-agent system where one OpenAI agent scans Kintone workspace layouts and another modifies data. The routing agent uses `list_apps` and `get_app_layout` to map the workspace before handing the task off to a specialized data entry agent. This structure keeps your OpenAI agents focused on specific Kintone tasks. The layout-reading agent never gets write access, while the writing agent only receives the specific target app ID to execute `update_record` safely.

Prevent runaway loops on Kintone MCP Server

Guardrails in this MCP Server setup stop your OpenAI agents from making endless Kintone API calls. When querying large databases, the agent uses `list_records` with strict limits, preventing it from fetching thousands of rows and burning through your OpenAI token budget. By setting `cacheToolsList=True` in your Python script, the OpenAI agent loads the schema once. It can quickly check `list_form_fields` to verify Kintone field codes before running any write operations, keeping execution times under control.

Setup guide

Set up Kintone MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Kintone tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Kintone tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Kintone tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Kintone Agent",
            instructions="You have access to Kintone tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the package using `pip install openai-agents` and initialize the MCP server. Pass the Vinkius URL to `MCPServerStreamableHttpParams` and load it into your agent constructor using the `mcp_servers` list.

Yes, you control access at the API token level. When the agent calls `list_apps`, it only sees the applications permitted by the Kintone credentials configured in your Vinkius dashboard.

The SDK catches the error and returns the API message to the agent. If `update_record` fails due to a missing field, the agent reads the error, corrects the JSON payload, and retries the operation.

Have your agent call `list_form_fields` before attempting to write data. This lets the agent inspect the required field codes and validation rules, ensuring the payload for `add_record` matches your app schema.

No, your raw database content remains secure. Only the specific records fetched via `get_record` or `list_records` are sent to the LLM context during active runs, and Vinkius processes these requests inside isolated, ephemeral execution sandboxes.

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