How to Use the Kintone MCP in Vercel AI SDK

Q: How do I use the Vercel AI SDK to add new records to a Kintone app?

You'll pass the addrecords tool from the MCP client to the generateText function. The tool expects a JSON array of record objects that match the fields in your Kintone app. The AI SDK handles the call and returns the result.

Q: What's the best way to display Kintone app fields dynamically using the Vercel AI SDK?

First, use listapps to get the app ID. Then, feed that ID to the getappfields tool. The result is a JSON object describing your app's structure, which you can then map over to render form inputs or table headers.

Build UIs that update live with your Kintone data. Stream records directly into your React app with the Vercel AI SDK.

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 Vercel AI SDK

Create your Vinkius account to connect Kintone to Vercel AI 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Kintone Data into Your UI

Your AI client can now pull data from Kintone and render it in real-time, right in your frontend. Instead of a loading spinner, your users will see records appearing one by one as they're fetched. This works by using the `list_records` tool and streaming the results directly into your React or Next.js components. It’s not just for reading data. You can build interactive forms that call `add_records` or `update_records` and see the changes reflect instantly in your app's display. The Vercel AI SDK handles the streaming; you just point it at this MCP Server endpoint.

Build Interactive Record Dashboards

Give your users a direct window into their Kintone apps. Your agent can use `list_apps` to populate a dropdown, letting a user pick an app. From there, you can fetch its structure with `get_app_fields` to dynamically build a data grid or form. When a user clicks a row, your AI client calls `get_record` to pull up the full details in a side panel. This isn't a pre-built widget. You're using the AI SDK to create a completely custom Kintone interface inside your own product.

Manage Workspaces with the Vercel AI SDK

This isn't just about record data. You can build admin tools that give a clear view of your Kintone environment. Use `get_space_details` to check on collaboration spaces, see who the members are, and monitor recent activity. Combine this with `list_apps` to create a full-fledged dashboard for managing your Kintone setup. Because the results stream, the UI feels responsive and fast, even when fetching a lot of information.

Setup guide

Set up Kintone MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Kintone tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Kintone transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

You'll pass the `add_records` tool from the MCP client to the `generateText` function. The tool expects a JSON array of record objects that match the fields in your Kintone app. The AI SDK handles the call and returns the result.

Yes. Create a search input in your React app that has your agent call the `list_records` tool on submit. Pass the user's input as the `query` argument to filter results directly in Kintone before they're streamed to your UI.

First, use `list_apps` to get the app ID. Then, feed that ID to the `get_app_fields` tool. The result is a JSON object describing your app's structure, which you can then map over to render form inputs or table headers.

Your Vinkius endpoint token secures the connection to this MCP server. The server itself holds the Kintone API credentials. Your frontend code and end-users never see or handle the Kintone keys.

The server only accesses the Kintone data needed for the specific tool you call, like app records, field settings, and space member lists. Your Vinkius token authenticates requests to the ephemeral, sandboxed server. The connection from your Vercel Edge Function to the MCP server is over HTTPS.

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