How to Use the Trakt MCP in Pydantic AI

Q: How does Pydantic AI query movie details using Trakt?

The agent uses getmovie for core data (runtime, rating). It also calls getrelatedmovies to suggest other content. Both tools return structured data that validates cleanly against defined schemas.

Q: Can I use Trakt with the Pydantic AI agent to track a user's history?

Yes. The gethistory tool pulls watch history, optionally filtered by type and ID. This requires an OAuth access token and gives you precise records of past viewing.

Q: What data does Trakt expose regarding TV show episodes for Pydantic AI?

The agent can use getshowepisodes to get episode number, title, overview, runtime, and the first aired date. This gives a granular view of every installment.

Q: Does Trakt support searching content with Pydantic AI?

It does. The search tool is versatile; it accepts type parameters ('episode', 'person', etc.) and returns results with titles, years, ratings, and synopses.

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

The getwatchlist tool touches the movie and/or show title metadata. This requires an OAuth access token for authentication.

The Trakt MCP Server feeds reliable movie and show data into your Pydantic AI agent, ensuring perfect validation every time.

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 Pydantic AI

Create your Vinkius account to connect Trakt to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate season structure with the MCP Server.

Use `get_show_seasons` to get all seasonal metadata for a TV show. Each result includes the season number, episode count, air date, rating, and overview. The structured output makes validation simple. This is ideal when your agent needs to process multi-year content series. It gives you a clean list of seasons, which can then be used to generate subsequent calls for episodes.

Access user collections using Pydantic AI.

The `get_collection` tool lets your agent retrieve items the authenticated user has gathered. It returns collected items along with full metadata and media info, which is great for custom dashboards. Remember that this requires OAuth access token handling to ensure you're pulling data only for the correct account.

Find popular content using Trakt MCP Server.

You can check trending or generally popular items with `get_popular` and `get_trending`. These tools return paginated results, which helps your agent manage large datasets of potential recommendations. The data structure includes viewer counts for both movies and shows, giving a clear metric of engagement. It’s simple to validate against expected result types.

Setup guide

Set up Trakt MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "trakt-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Trakt tools.",
)

result = await agent.run("List recent Trakt transactions")
print(result.output)

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 Pydantic AI

The agent uses `get_movie` for core data (runtime, rating). It also calls `get_related_movies` to suggest other content. Both tools return structured data that validates cleanly against defined schemas.

Yes. The `get_history` tool pulls watch history, optionally filtered by type and ID. This requires an OAuth access token and gives you precise records of past viewing.

The agent can use `get_show_episodes` to get episode number, title, overview, runtime, and the first aired date. This gives a granular view of every installment.

It does. The `search` tool is versatile; it accepts type parameters ('episode', 'person', etc.) and returns results with titles, years, ratings, and synopses.

The `get_watchlist` tool touches the movie and/or show title metadata. 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