How to Use the Kintone MCP in Mastra AI

Q: How do I make a Mastra AI agent work with multiple Kintone apps?

Have your agent call listapps at the beginning of its run. It can then store the IDs for your 'Leads' and 'Contacts' apps in variables to use in subsequent addrecord or listrecords calls.

Q: Can I build a workflow in Mastra AI that updates a Kintone record and then notifies someone?

Yes, that's a perfect use case. The agent would use the updaterecord tool from this server, and then, in the same workflow, use a separate tool for sending an email or Slack message.

Build failure-proof Kintone automations with Mastra AI. Run multi-step workflows that sync records, handle errors, and just work.

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 Mastra AI

Create your Vinkius account to connect Kintone to Mastra 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Kintone Data Entry

A Mastra AI agent can process an incoming webhook, pull out customer data, and use `add_record` to create a new entry in your Kintone CRM app. This MCP integration is a solid first step for any automation. But what if the Kintone API is down? Mastra's built-in retries kick in. Your agent will try the `add_record` call again with exponential backoff, ensuring the data gets in without you writing retry logic.

Build Smart Kintone Processes

Your agent can pull a record with `get_record`. Based on a field's value—say, `status` is 'urgent'—it can branch its logic. Urgent tickets get pushed to a Slack channel, normal ones just get updated. This isn't just a simple if/then. You can create complex chains. If `update_record` fails, the agent could try to find a manager using `list_space_members` and send them a notification. Mastra handles the state.

Your Mastra AI MCP Server

Before running a big job, your agent should check its environment. It can start with `list_apps` to find the correct app ID. This prevents it from accidentally writing data to your production app during a test run. It can go deeper, using `get_app_details` to check the app's name and `list_form_fields` to validate that the fields it expects are actually there. This is a solid use for an MCP Server, making your automation less brittle.

Setup guide

Set up Kintone MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Kintone tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "kintone-mcp-client",
  servers: {
    "kintone-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Kintone Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Kintone tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Kintone transactions"
);
console.log(result.text);

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 Mastra AI

Yes, this is a core strength of Mastra AI. Its workflow engine has automatic retries with exponential backoff, so it will keep trying the `add_record` call if the Kintone API is temporarily unavailable.

Have your agent call `list_apps` at the beginning of its run. It can then store the IDs for your 'Leads' and 'Contacts' apps in variables to use in subsequent `add_record` or `list_records` calls.

Yes, that's a perfect use case. The agent would use the `update_record` tool from this server, and then, in the same workflow, use a separate tool for sending an email or Slack message.

Yes. Vinkius provides a sandboxed connection with a single token, which isolates your agent's access. You aren't exposing your main Kintone credentials.

This MCP server only interacts with the Kintone application and record data you explicitly command it to. All connections are ephemeral and secured through your Vinkius token, not direct Kintone credentials.

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