How to Use the Gotify MCP in Vercel AI SDK

Q: Can Vercel AI SDK stream message histories from Gotify in real-time?

Yes, by calling getmessages inside streamText. The SDK handles the incoming JSON payload and streams the message text block-by-block directly into your React component.

Q: How does the MCP Server handle application token generation?

Your agent calls createapplication to generate a new token. The Vercel AI SDK receives this token in the tool execution result, allowing you to display it immediately on screen.

Send and display Gotify alerts in real-time directly inside your React app with Vercel AI SDK and this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Gotify MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Push alerts to UI components via `send_message`

The `send_message` tool lets your Vercel AI SDK agent dispatch instant alerts directly to your self-hosted Gotify server. Your React frontend displays the notification payload immediately as the edge function executes, bypassing slow UI spinners. You pass the `GOTIFY_APP_TOKEN` to the MCP Server, and your code feeds the tool directly into `streamText`. This setup keeps your users updated on background jobs without making them wait for a manual refresh.

Manage apps on the fly with Vercel AI SDK

The `create_application` tool creates new notification channels inside your Gotify instance directly from your chat interface. Your user asks for a new alert feed, and the agent spins it up instantly, returning the brand-new application token to the UI. Combine this with `delete_application` to prune dead channels without leaving your Next.js dashboard. Every state update flows through standard React hooks, making your admin panel feel incredibly fast.

Fetch and render live notification feeds

The `get_messages` tool pulls the latest notification history from your Gotify server using the client token. Your Vercel AI SDK frontend renders this message stream on the fly, allowing users to scroll through past alerts in a clean list. You can clean up the feed instantly by invoking `delete_all_messages` or `delete_message` directly from the chat. It keeps the database clean and ensures your interface only shows what is relevant right now.

Setup guide

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

You set the server URL and tokens as environment variables in your Next.js project. Pass these to the `createMCPClient` constructor, then expose the tools directly inside your `generateText` call.

Yes, the transport runs on standard HTTP POST requests, which means it is fully compatible with Vercel Edge Functions. You get sub-millisecond connection times to your Gotify instance without cold starts.

Yes, by calling `get_messages` inside `streamText`. The SDK handles the incoming JSON payload and streams the message text block-by-block directly into your React component.

Your agent calls `create_application` to generate a new token. The Vercel AI SDK receives this token in the tool execution result, allowing you to display it immediately on screen.

This integration only processes your Gotify message strings and app tokens within Vercel's secure environment. No third-party servers store your notification logs or access 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