How to Use the Kintone MCP in Mastra AI

Q: How can I use Mastra AI to sync data between two Kintone apps?

Create a Mastra agent that calls listrecords on the source app. Then, loop through the results and use addrecords or updaterecords to push the data into the destination app. Mastra's engine will handle pagination and retries for you.

Q: Can my Mastra AI agent get details about a Kintone collaboration space?

Yes, the getspacedetails tool is perfect for this. Provide a space ID, and your agent will get back information about the space, including its members. You could use this to automate user onboarding or offboarding tasks.

Q: What's the process for updating multiple Kintone records at once with Mastra AI?

The updaterecords tool is designed for bulk operations. Your Mastra AI agent just needs to construct a JSON array where each object has the record id to update and the new field data. The MCP server handles the batch request to Kintone.

Q: Does this MCP server support Kintone's query language?

It does. The listrecords tool accepts an optional query string. Your agent can pass any valid Kintone query, like status = "In Progress", to filter the records returned from the API.

Build resilient, multi-step Kintone workflows with Mastra AI. Automate record creation, updates, and approvals with built-in retries.

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 Complex Business Logic

Mastra AI is built for workflows that have more than one step. You can create an agent that first uses `get_record` to check a record's status in Kintone. Based on the result, it can then decide whether to call `update_records` to approve it or trigger another action. This isn't just a simple script. Mastra's workflow engine lets you build conditional branches. For example: if a record from `list_records` meets certain criteria, update it; otherwise, send a notification.

Create Fault-Tolerant Kintone Integrations

APIs fail. Mastra AI is designed for that. If a call to `add_records` fails because the Kintone API is temporarily down, Mastra can automatically retry the operation with exponential backoff. You don't have to write that logic yourself. You can also add human-in-the-loop approvals. Before your agent executes a `delete_records` command, you can configure it to require confirmation from an admin. This gives you automation with a safety net.

Govern Your Kintone Apps with this MCP Server

Use Mastra AI to build governance workflows that keep your Kintone environment clean. Schedule a daily job that runs `list_apps`, then iterates through them with `get_app_fields` to check for non-standard field names or missing descriptions. If an app is out of compliance, the agent can automatically use `update_records` in a central "tasks" app to assign a fix to the app's owner. This turns governance from a manual checklist into an automated process.

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-alternative-mcp-client",
  servers: {
    "kintone-alternative-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

Create a Mastra agent that calls `list_records` on the source app. Then, loop through the results and use `add_records` or `update_records` to push the data into the destination app. Mastra's engine will handle pagination and retries for you.

Yes, the `get_space_details` tool is perfect for this. Provide a space ID, and your agent will get back information about the space, including its members. You could use this to automate user onboarding or offboarding tasks.

The `update_records` tool is designed for bulk operations. Your Mastra AI agent just needs to construct a JSON array where each object has the record `id` to update and the new field data. The MCP server handles the batch request to Kintone.

It does. The `list_records` tool accepts an optional `query` string. Your agent can pass any valid Kintone query, like `status = "In Progress"`, to filter the records returned from the API.

This MCP server processes Kintone record data, application schemas, and workspace details on your behalf. Each request is handled in a zero-trust, ephemeral environment that is destroyed after execution. Your Mastra AI agent communicates with the server over a secure, authenticated channel.

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