How to Use the Kintone MCP in AutoGen

Q: How do I load Kintone tools into AutoGen?

Install autogen-extmcp and use mcpservertools with your StreamableHttpServerParams. The McpToolAdapter automatically converts the schemas for your AssistantAgent.

Q: Can AutoGen agents read Kintone app settings?

Yes. Agents call getappfields to inspect the drag-and-drop form configurations. They use this information to negotiate the correct data format before attempting writes.

Q: How do multiple AutoGen agents handle Kintone records?

One agent can use listrecords to pull data, while another analyzes it. They pass the context back and forth in the conversation thread until they reach a consensus on what to do next.

Give your AutoGen multi-agent systems direct access to manage Kintone records and workspaces.

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 AutoGen

Create your Vinkius account to connect Kintone to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Record Management

This MCP Server enables your Microsoft AutoGen agents to interact with your business databases using `add_records` and `update_records`. A research agent might compile data, while a secondary validation agent reviews the formatting before pushing it to the app. They debate the correct structure based on the schema. If the validation agent spots a missing required field, it rejects the payload, forcing the first agent to correct the JSON array before the final API call executes.

Discover Kintone MCP Server Tools

Mapping out your available environments happens through the `list_apps` and `get_app_fields` tools. Your agents query these endpoints to establish ground truth about the data structure they are supposed to manipulate. A dedicated planner agent uses this metadata to assign tasks. It reads the field settings, determines which agent is best suited to handle specific data types, and directs the workflow without human intervention.

Automate Space Maintenance

Managing team environments relies on the `get_space_details` and `delete_records` tools. An administrative agent can monitor specific spaces, pulling details to check activity levels or identify obsolete entries. When it finds old data, it proposes a deletion plan. A separate compliance agent reviews the proposal, checks it against your business rules, and either approves or denies the removal of those records.

Setup guide

Set up Kintone MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Kintone tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Kintone_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Kintone data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Kintone_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Kintone data")
    print(result.messages[-1].content)

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 AutoGen

Install `autogen-ext[mcp]` and use `mcp_server_tools` with your `StreamableHttpServerParams`. The `McpToolAdapter` automatically converts the schemas for your `AssistantAgent`.

Yes. Agents call `get_app_fields` to inspect the drag-and-drop form configurations. They use this information to negotiate the correct data format before attempting writes.

One agent can use `list_records` to pull data, while another analyzes it. They pass the context back and forth in the conversation thread until they reach a consensus on what to do next.

No. AutoGen handles the schema translation natively. You just pass the generated tools list into the agent constructor and start the conversation.

Your team collaboration spaces and custom app fields remain strictly bound to the ephemeral runtime. Vinkius provisions a single-use environment that drops all session memory the moment your agents conclude their HTTP transport connection.

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