How to Use the Umami (Privacy Analytics) MCP in Vercel AI SDK

Q: Can I see website activity in real time with Umami (Privacy Analytics) and Vercel AI SDK?

Absolutely. The getrealtimestats tool lets you pull stats from the last 30 minutes, streaming them directly into your Next.js or Svelte UI via the Vercel AI SDK.

Q: How do I manage users while developing with Umami (Privacy Analytics) and Vercel AI SDK?

You can use admin tools like createuser, updateuser, or even delete accounts using deleteuser. These actions are managed through the MCP Server's administrative endpoints.

Q: Does Umami (Privacy Analytics) support data date range queries when integrated with Vercel AI SDK?

Yes. The getwebsitedaterange tool lets you check what periods of time are available for analysis. This ensures your application only requests valid historical data.

Real-time analytics streaming directly into your UI using 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 Umami (Privacy Analytics) MCP to Vercel AI SDK

Create your Vinkius account to connect Umami (Privacy Analytics) 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 Umami (Privacy Analytics) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Live Traffic Data

You can stream real-time visitor counts and event activity. Call `get_realtime_stats` to show users what's happening in the last 30 minutes, making your app feel instant. This works great for showing live data feeds on a dashboard built with Vercel AI SDK. You get immediate updates by fetching metrics like pageviews and sessions using `get_website_pageviews`.

Build Conversion Funnels

Map out user journeys and see where people drop off. Use the dedicated function `create_funnel_report` to visualize conversion steps. Need detailed breakdowns? You can call `get_website_event_data_events` which lists event names and their counts, giving you granular data for your client-facing reporting.

Track User Retention Metrics

Understand how long users stick around. Run a user retention report by calling `create_retention_report`. This tells you which parts of the marketing funnel are keeping people engaged. Want to see overall site performance? Grab summarized stats with `get_website_stats` for pageviews and total visitors over any given time range.

Setup guide

Set up Umami (Privacy Analytics) 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 Umami (Privacy Analytics) 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 Umami (Privacy Analytics) 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 Umami. 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 Umami (Privacy Analytics) 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 Umami (Privacy Analytics) MCP in Vercel AI SDK

The MCP Server keeps your analytics secure. Since you're building a user-facing product with the Vercel AI SDK, all interactions are handled through streaming calls, meaning raw data never leaves your managed environment.

Absolutely. The `get_realtime_stats` tool lets you pull stats from the last 30 minutes, streaming them directly into your Next.js or Svelte UI via the Vercel AI SDK.

This MCP Server handles event data, session details, and user metrics. You can get everything from specific pageviews (`get_website_pageviews`) to detailed property counts using `get_website_event_data_fields`.

You can use admin tools like `create_user`, `update_user`, or even delete accounts using `delete_user`. These actions are managed through the MCP Server's administrative endpoints.

Yes. The `get_website_daterange` tool lets you check what periods of time are available for analysis. This ensures your application only requests valid historical 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