How to Use the Trakt MCP in Vercel AI SDK

Q: How do I find a movie using Trakt with the Vercel AI SDK?

Just call the search tool and specify 'movie' as the type. Your agent returns titles, years, ratings, and synopses. Since this data streams via the Vercel AI SDK, you can show those results appearing live on your page.

Q: Can Trakt help me track a user's watchlist with the Vercel AI SDK?

Yes, use getwatchlist. This tool requires an OAuth access token and returns all movies or shows the authenticated user added to their list. The results flow right into your UI using the streaming capability of the Vercel AI SDK.

Q: What data does Trakt provide about a TV show for my app built with Vercel AI SDK?

The getshow tool gives you title, year, overview, status, runtime, and genres. If you need deeper context, use getshowepisodes to grab episode numbers, titles, and first aired dates.

Q: Does Trakt provide historical viewing data for Vercel AI SDK?

Absolutely. The getwatched tool retrieves items with play counts and last watched timestamps. It needs an OAuth access token to pull the authenticated user's history, making it ideal for tracking usage in your application.

Q: What data privacy considerations exist when using Trakt MCP Server?

When running tools like getwatched or getwatchlist, the server touches the user’s viewing history and watchlist items. Always handle OAuth access tokens securely, as this is sensitive activity data.

Show your users real-time data streams with 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 Trakt MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Displaying Live Watch Data with Trakt

When you call the `get_watched` tool, your agent instantly pulls play counts and last watched timestamps. This data streams directly to your UI so users see their viewing history populating in real-time, not after a loading spinner. It's perfect for building dashboards where seeing immediate updates matters. You can build out the whole experience using the Vercel AI SDK because the tool results stream right into the user interface.

Searching and Filtering with Trakt MCP Server

The `search` tool lets your agent pull titles, years, ratings, genres, and synopses for movies, shows, episodes, people, or lists. You can pass the `type` parameter to narrow down results immediately. This is crucial for any user-facing product where quick filtering is key. Use this capability to power advanced search bars within your React or Next.js frontend.

Getting Detailed Movie/Show Info with Trakt

Use `get_movie` or `get_show` when you need a full breakdown of content, including runtime, rating, genre, and poster URLs. You get the whole picture in one go. This capability lets your agent present rich media data immediately upon request. When streaming these structured results via Vercel AI SDK, the user experience feels instant.

Setup guide

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

Just call the `search` tool and specify 'movie' as the type. Your agent returns titles, years, ratings, and synopses. Since this data streams via the Vercel AI SDK, you can show those results appearing live on your page.

Yes, use `get_watchlist`. This tool requires an OAuth access token and returns all movies or shows the authenticated user added to their list. The results flow right into your UI using the streaming capability of the Vercel AI SDK.

The `get_show` tool gives you title, year, overview, status, runtime, and genres. If you need deeper context, use `get_show_episodes` to grab episode numbers, titles, and first aired dates.

Absolutely. The `get_watched` tool retrieves items with play counts and last watched timestamps. It needs an OAuth access token to pull the authenticated user's history, making it ideal for tracking usage in your application.

When running tools like `get_watched` or `get_watchlist`, the server touches the user’s viewing history and watchlist items. Always handle OAuth access tokens securely, as this is sensitive activity 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