How to Use the Immich (Google Photos Alternative) MCP in Vercel AI SDK

Q: How do I stream photo metadata from Immich (Google Photos Alternative) using Vercel AI SDK?

You install the @ai-sdk/mcp package and initialize an MCP client pointing to your Vinkius server URL. Pass the retrieved tools directly into your streamText call to let your agent query listassets and push the metadata to your frontend.

Q: How does this MCP Server handle user management tasks in Immich (Google Photos Alternative) inside Vercel AI SDK?

The server exposes admin tools like createuser and listusers as standard JSON schemas. Your edge functions pass these tools to the SDK, allowing authorized agents to manage accounts dynamically.

Q: What is the correct setup sequence for this MCP integration?

Install ai and @ai-sdk/mcp first. Initialize the client using createMCPClient with your Vinkius URL, retrieve the tools, and remember to call mcpClient.close() when the execution context ends.

Stream self-hosted media metadata and asset updates directly into your Next.js frontend 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 Immich (Google Photos Alternative) MCP to Vercel AI SDK

Create your Vinkius account to connect Immich (Google Photos Alternative) 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 Immich (Google Photos Alternative) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Render live photo feeds using Vercel AI SDK

This MCP Server lets your application query your self-hosted database to fetch media assets instantly. By calling `list_assets` and `get_asset`, the Vercel AI SDK pipes the raw image metadata straight to your UI components without making the user wait for a full page reload. You can build a custom photo wall where your agent handles search queries and streams the matching images live. If a user wants to find a specific image, the agent triggers `get_asset` to pull down the direct path and metadata, rendering the image container the millisecond the database responds.

Build instant albums in React

Organizing your media library becomes interactive when your agent uses `create_album` and `update_album` inside a streaming chat interface. As the user types instructions to group their recent trip photos, the Vercel AI SDK streams the step-by-step execution status directly into the chat bubble. The agent can immediately follow up by calling `list_albums` to show the updated collection sidebar. Because the tool outputs stream as JSON parts, your UI updates the folder structure dynamically without requiring manual page refreshes.

Manage tags and faces on Edge Functions

Running your photo management on edge nodes is straightforward when you hook up this MCP Server to your edge routes. Your AI client can process face-tagging requests by invoking `create_tag` and binding it to specific assets on the fly. Since the Vercel AI SDK works flawlessly in lightweight environments, you don't need a heavy server to run these classification tasks. Checking server health via `get_server_info` allows your agent to safely execute `update_tag` and keep your self-hosted library organized.

Setup guide

Set up Immich (Google Photos Alternative) 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 Immich (Google Photos Alternative) 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 Immich (Google Photos Alternative) 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 Immich. 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 Immich (Google Photos Alternative) 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 Immich (Google Photos Alternative) MCP in Vercel AI SDK

You install the `@ai-sdk/mcp` package and initialize an MCP client pointing to your Vinkius server URL. Pass the retrieved tools directly into your `streamText` call to let your agent query `list_assets` and push the metadata to your frontend.

Yes, because the SDK streams tool call arguments before execution finishes. Your UI can optimistically render the new album placeholder the moment the agent triggers `create_album`.

The server exposes admin tools like `create_user` and `list_users` as standard JSON schemas. Your edge functions pass these tools to the SDK, allowing authorized agents to manage accounts dynamically.

Install `ai` and `@ai-sdk/mcp` first. Initialize the client using `createMCPClient` with your Vinkius URL, retrieve the tools, and remember to call `mcpClient.close()` when the execution context ends.

Absolutely. Your raw photos, videos, and facial recognition profiles never pass through third-party servers because Vinkius runs inside a zero-trust, ephemeral V8 Isolate sandbox. Only the metadata strictly required for tools like `list_persons` or `get_asset` is processed, keeping your family library completely private.

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