How to Use the Trakt MCP in LangChain

Q: How do I use Trakt with LangChain to find related content?

First, call getmovie using the title. The output gives you metadata. You can then pass that ID into getrelatedmovies. This chaining process lets your agent discover new titles based on known data.

Q: What is the best way to handle user watch history with Trakt and LangChain?

You call gethistory using the necessary OAuth token. If you need specific filters, you can pass them in that initial request. The output gives you a clean list of IDs and play counts for subsequent processing.

Q: Does Trakt support checking trending content with LangChain?

Yes. Use the gettrending tool to pull currently popular movies or shows. This data is useful for an agent needing real-time context on what users are actively watching right now.

Q: When should I use Trakt for searching titles with LangChain?

If you don't know the exact title, start by calling search. You can narrow down the results using the type parameter (e.g., 'movie' or 'show'). The resulting IDs are what you pass to more specific retrieval tools.

Building multi-step pipelines with Trakt and LangChain.

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 LangChain

Create your Vinkius account to connect Trakt to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Step Content Discovery for LangChain

The `get_movie` tool pulls core metadata like runtime, rating, and genres. You can chain that output directly into the `get_related_movies` tool to build a complete content graph. This capability lets your ReAct agent decide on the optimal path: first check `search` for titles, then use the resulting ID in `get_show_episodes` to get air dates. It's about linking data together.

Managing Watchlist and History with MCP Server

Your agent needs access tokens to handle personal data. Use the `get_watchlist` tool to pull what a user saved, then combine that result set into calling `get_history`. This allows your workflow to analyze both intended viewing content and actual viewing patterns. The system handles the OAuth credentials automatically, so you don't have to build state management for basic history retrieval.

Structured Data Retrieval via Trakt MCP Server

The `get_show` tool provides detailed info on a TV series. You can then use the show name and ID output as input for both `get_show_seasons` and `get_show_episodes`. This structured sequence ensures you get comprehensive season breakdowns, episode counts, and air dates. This reliable flow is critical when building pipelines that require multiple dependent data points.

Setup guide

Set up Trakt MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Trakt tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "trakt-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Trakt transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

First, call `get_movie` using the title. The output gives you metadata. You can then pass that ID into `get_related_movies`. This chaining process lets your agent discover new titles based on known data.

You call `get_history` using the necessary OAuth token. If you need specific filters, you can pass them in that initial request. The output gives you a clean list of IDs and play counts for subsequent processing.

Yes. Use the `get_trending` tool to pull currently popular movies or shows. This data is useful for an agent needing real-time context on what users are actively watching right now.

If you don't know the exact title, start by calling `search`. You can narrow down the results using the type parameter (e.g., 'movie' or 'show'). The resulting IDs are what you pass to more specific retrieval tools.

The server touches personal viewing data, specifically the user's watch history and their watchlist items. These operations require an OAuth access token for authorization.

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