How to Use the Kisi MCP in Vercel AI SDK

Q: How do I initialize the Kisi MCP Server with Vercel AI SDK?

Run npm install @ai-sdk/mcp. Use createMCPClient with an HTTP transport pointing to your Vinkius endpoint. Pass the resulting tools to your streamText function.

Q: Can Vercel AI SDK stream the results of a Kisi door unlock?

Yes. When the agent executes unlockdoor, the success response streams back to the client immediately. You trigger a UI state change the millisecond the API confirms the door is open.

Connect Kisi to your Vercel AI SDK frontend to stream physical access events and lock statuses directly into your React dashboard.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kisi MCP to Vercel AI SDK

Create your Vinkius account to connect Kisi 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 Kisi with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Kisi physical access data into Vercel AI SDK

Building a live security dashboard means you need data fast. When your agent calls `list_places` or `list_locks`, the Vercel AI SDK streams those hardware states straight to your user's browser. No loading spinners while you wait for the MCP Server to finish checking the building. You can pipe `get_lock_details` right into a Next.js server component. If an office manager needs to see who has access to the server room, the UI populates the `list_users` output as the AI reads it. It feels instant because it is.

Trigger physical doors from custom interfaces

Reading data is fine, but sometimes you need to let someone in. You can wire the `unlock_door` tool to a simple chat interface or a panic button in your Svelte app. The user asks the AI to open the front door, the agent verifies their identity, and fires the command. You get immediate confirmation back. The AI runs `get_lock_details` immediately after the unlock event to confirm the hardware actually responded. Your frontend updates the door status indicator in real-time.

Expose access group audits to end users

IT admins hate digging through nested menus to figure out who has what keys. Give them a conversational interface that hits `list_access_groups` and `list_role_assignments` simultaneously. They ask 'Who can enter the lab?', and the agent pulls the exact list. Since you control the prompt, you can format this raw Kisi API data into clean tables using generative UI. The agent cross-references the IDs with `list_users` and renders a plain-English roster of everyone holding lab credentials.

Setup guide

Set up Kisi 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 Kisi 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 Kisi 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 Kisi. 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 Kisi 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 Kisi MCP in Vercel AI SDK

Run `npm install @ai-sdk/mcp`. Use `createMCPClient` with an HTTP transport pointing to your Vinkius endpoint. Pass the resulting tools to your `streamText` function.

Yes. When the agent executes `unlock_door`, the success response streams back to the client immediately. You trigger a UI state change the millisecond the API confirms the door is open.

Writing custom API wrappers takes time and breaks when endpoints change. The MCP standard gives your Vercel AI SDK agent immediate, typed access to all 9 Kisi tools without writing a single fetch request.

Vinkius manages the underlying Kisi API keys. Your Vercel AI SDK application just needs a single endpoint token to connect to the managed server.

The server processes highly sensitive physical security data, including employee user IDs, physical location coordinates via `get_place_details`, and role assignments. Vinkius runs this connection in an ephemeral V8 Isolate Sandbox. The sandbox spins up to execute the door command and immediately self-destructs, leaving zero residual data.

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