How to Use the Trakt MCP in Cursor

Q: How do I use Trakt with Cursor?

Just add the server configuration in your project's .cursor/mcp.json file, then enable Agent mode in the chat. Your AI client will recognize the tools and allow you to call them directly while writing code.

Q: Can I get a complete cast and crew list for any movie?

Yes. You run getmoviepeople against the movie ID. The response gives names, Trakt IDs, job titles (for crew), and character names (if they're part of the cast). It’s structured data you can easily parse.

Q: What is the best way to search using Trakt and Cursor?

Use the search tool, passing in a specific type parameter like 'show', 'movie', or 'episode'. This limits the results set right away, making your code cleaner because you know exactly what kind of object you'll be dealing with.

Q: Does Trakt handle user watchlist data for Cursor?

It does. The getwatchlist tool fetches all the movies and/or shows a user has saved. Since it requires an OAuth token, you'll need to pass that securely when your agent calls the function.

Inject live Trakt movie and show metadata directly into your code with Cursor.

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 Cursor

Create your Vinkius account to connect Trakt to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fetch deep, nested media details

Writing a script that needs full context on a piece of media? You can use `get_show` to grab core data (overview, runtime, genre) and then follow up with `get_show_episodes`. This lets you write functions that take a show ID and return a structured list of episodes, including their air dates. It’s about chaining calls: first get the container, then iterate over the contents. No mocking needed; it's live API responses directly in your code block.

Calculate rating distributions programmatically

If you're building a review aggregator, you need more than just an average score. The `get_show_ratings` tool returns total ratings, the average score, *and* vote counts per specific rating level (e.g., how many 10/10 votes vs. 7/10 votes). This is crucial for accurate data analysis. Your agent can process this JSON response to calculate weighted metrics right inside your editor.

Manage and retrieve user content collections

The `get_collection` tool requires OAuth but delivers a list of items with full metadata. You can write code that iterates over these collected items, pulling out their media info and associated data points. This makes it simple to build internal dashboards or tools that reference user-saved content lists accurately.

Setup guide

Set up Trakt MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Trakt MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Trakt transactions." If the MCP tools are loaded correctly, Cursor will call the Trakt tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "trakt-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Cursor

Just add the server configuration in your project's `.cursor/mcp.json` file, then enable Agent mode in the chat. Your AI client will recognize the tools and allow you to call them directly while writing code.

Yes. You run `get_movie_people` against the movie ID. The response gives names, Trakt IDs, job titles (for crew), and character names (if they're part of the cast). It’s structured data you can easily parse.

Use the `search` tool, passing in a specific type parameter like 'show', 'movie', or 'episode'. This limits the results set right away, making your code cleaner because you know exactly what kind of object you'll be dealing with.

It does. The `get_watchlist` tool fetches all the movies and/or shows a user has saved. Since it requires an OAuth token, you'll need to pass that securely when your agent calls the function.

This server touches user activity and preference data. Specifically, `get_watched` handles play counts and last watched timestamps, while `get_watchlist` manages saved items.

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