How to Use the Trakt MCP in OpenAI Agents SDK

Q: How does the OpenAI Agents SDK query movie data using Trakt?

Your agent uses getmovie to pull basic info like runtime and ratings. It also uses search if the user doesn't know the exact title, giving them a list of options first.

Q: Can I use Trakt with the OpenAI Agents SDK to check watch history?

Yep. The agent calls getwatched, which requires an OAuth token. It returns play counts and last watched timestamps, letting you track user activity precisely.

Q: What data does Trakt expose regarding show metadata for the OpenAI Agents SDK?

You can use getshow for basic details (status, network). For deeper dives, getshowseasons gives you season numbers, episode counts, and air dates.

Q: Does Trakt support finding related content via the OpenAI Agents SDK?

It does. You can run getrelatedmovies or getrelatedshows. Both tools return titles, years, ratings, and poster URLs so you can suggest next viewing material.

Q: If I need to know about a user's personal list, what data type does Trakt touch?

The getwatchlist tool touches the user's saved titles (movies and/or shows). This requires an OAuth access token for authentication.

Trakt MCP Server helps your OpenAI Agents SDK access movie and show data instantly, right where you need it.

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 OpenAI Agents SDK

Create your Vinkius account to connect Trakt to OpenAI Agents 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Search content with the MCP Server.

The `search` tool lets your agent quickly find anything—movies, shows, episodes, or people. You just pass a type parameter ('movie', 'show', etc.) to narrow results down. It returns titles, years, ratings, and synopses for immediate use. You'll never have to guess what content is available. If the user asks about something specific, `search` handles it immediately, giving you IDs and enough context to proceed with other operations.

Monitor watch progress using OpenAI Agents SDK.

Need to know if a user watched an episode? Use `get_watched`. This tool checks play counts and provides the last watched timestamps for authenticated users. It's perfect for building tracking features. Also, you can check their curated lists by calling `get_watchlist`. Both tools require OAuth access tokens, so your agent handles that authentication flow before pulling the necessary data.

Retrieve deep details on any title.

The `get_movie` and `get_show` tools grab all the key info you need. They return titles, runtime, ratings, genres, and poster URLs right out of the gate. It's a one-shot deal. Furthermore, if you need to know who made it, use `get_movie_people` or `get_show_people`. These tools provide names, Trakt IDs, job titles, and even character names for cast members.

Setup guide

Set up Trakt MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Trakt tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Trakt tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Trakt tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Trakt Agent",
            instructions="You have access to Trakt tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Your agent uses `get_movie` to pull basic info like runtime and ratings. It also uses `search` if the user doesn't know the exact title, giving them a list of options first.

Yep. The agent calls `get_watched`, which requires an OAuth token. It returns play counts and last watched timestamps, letting you track user activity precisely.

You can use `get_show` for basic details (status, network). For deeper dives, `get_show_seasons` gives you season numbers, episode counts, and air dates.

It does. You can run `get_related_movies` or `get_related_shows`. Both tools return titles, years, ratings, and poster URLs so you can suggest next viewing material.

The `get_watchlist` tool touches the user's saved titles (movies and/or shows). This requires an OAuth access token for authentication.

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