How to Use the Kintone MCP in Pydantic AI

Q: How do I register the Kintone MCP Server in Pydantic AI?

Install the slim package with pip install "pydantic-ai-slimmcp" to handle the MCP connection. Initialize MCPToolset with your HTTP endpoint and pass this toolset directly into the Agent constructor using the toolsets argument.

Q: Can my Pydantic AI agent delete records from Kintone?

Yes, you can use the deleterecords tool by passing an array of record IDs. The agent validates the list of IDs to ensure they are formatted correctly before sending the delete request to the API.

Q: Where are my Kintone app layouts and schemas stored?

Schemas fetched via getapplayout are parsed in-memory during the agent's run. Vinkius handles the underlying MCP authentication tokens securely, and no layout configurations or field definitions are stored permanently.

Build type-safe agents that read and write Kintone records with strict validation using Pydantic AI 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 Pydantic AI

Create your Vinkius account to connect Kintone to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe record updates with Pydantic AI

Stop worrying about malformed JSON payloads breaking your Kintone database. Pydantic AI validates every response from this MCP Server against Python type hints at runtime, ensuring your agent never sends invalid fields to your apps. If your Pydantic AI agent attempts to run `update_record` with a string where an integer is expected, the framework raises a validation error immediately. This prevents corrupted data from ever reaching your production Kintone database.

Validate Kintone form schemas before writing

Your Pydantic AI agent can inspect the exact structure of your database before attempting to insert new entries. By calling `list_form_fields`, the agent retrieves the Kintone field types and required fields directly from the API. The agent then maps these fields to Pydantic models. When executing `add_record` in Kintone, the framework guarantees the payload matches the form schema, eliminating runtime API errors caused by mismatched fields.

Clean app discovery without silent failures

Keep your multi-app Kintone workflows reliable. The agent uses `list_apps` to locate the correct target database and `get_app_details` to verify its status before running any data operations. Because Pydantic AI enforces strict data contracts, any unexpected Kintone API response triggers an immediate, readable traceback. This ensures your agent fails loudly and safely instead of executing operations on the wrong application.

Setup guide

Set up Kintone MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "kintone-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Kintone tools.",
)

result = await agent.run("List recent Kintone transactions")
print(result.output)

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 Pydantic AI

Install the slim package with `pip install "pydantic-ai-slim[mcp]"` to handle the MCP connection. Initialize `MCPToolset` with your HTTP endpoint and pass this toolset directly into the `Agent` constructor using the `toolsets` argument.

It prevents silent data corruption. When your agent fetches records using `get_record` or `list_records`, the incoming data is validated against strict Pydantic models before your business logic processes it.

Yes, you can use the `delete_records` tool by passing an array of record IDs. The agent validates the list of IDs to ensure they are formatted correctly before sending the delete request to the API.

Yes, the framework is model-agnostic. You can run your agent using local models or commercial APIs, and they will all be able to call the tools on this server to manage your business data.

Schemas fetched via `get_app_layout` are parsed in-memory during the agent's run. Vinkius handles the underlying MCP authentication tokens securely, and no layout configurations or field definitions are stored permanently.

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