Trakt MCP Server for OpenAI Agents SDK 18 tools — connect in under 2 minutes
The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Trakt through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
async with MCPServerStreamableHttp(
url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
) as mcp_server:
agent = Agent(
name="Trakt Assistant",
instructions=(
"You help users interact with Trakt. "
"You have access to 18 tools."
),
mcp_servers=[mcp_server],
)
result = await Runner.run(
agent, "List all available tools from Trakt"
)
print(result.final_output)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About Trakt MCP Server
Connect to Trakt and explore the world's most popular TV and movie tracking platform through natural conversation.
The OpenAI Agents SDK auto-discovers all 18 tools from Trakt through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Trakt, another analyzes results, and a third generates reports, all orchestrated through Vinkius.
What you can do
- Search — Find movies, TV shows, episodes and people by title or name
- Movie Details — Get ratings, cast, crew, genres and related movies
- Show Details — Get seasons, episodes, cast, ratings and related shows
- Trending — See what's currently trending on Trakt in real-time
- Popular — Discover the most popular movies and shows
- Calendar — Get upcoming episode premieres and air dates
The Trakt MCP Server exposes 18 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect Trakt to OpenAI Agents SDK via MCP
Follow these steps to integrate the Trakt MCP Server with OpenAI Agents SDK.
Install the SDK
Run pip install openai-agents in your Python environment
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com
Run the script
Save the code above and run it: python agent.py
Explore tools
The agent will automatically discover 18 tools from Trakt
Why Use OpenAI Agents SDK with the Trakt MCP Server
OpenAI Agents SDK provides unique advantages when paired with Trakt through the Model Context Protocol.
Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
Trakt + OpenAI Agents SDK Use Cases
Practical scenarios where OpenAI Agents SDK combined with the Trakt MCP Server delivers measurable value.
Automated workflows: build agents that query Trakt, process the data, and trigger follow-up actions autonomously
Multi-agent orchestration: create specialist agents. one queries Trakt, another analyzes results, a third generates reports
Data enrichment pipelines: stream data through Trakt tools and transform it with OpenAI models in a single async loop
Customer support bots: agents query Trakt to resolve tickets, look up records, and update statuses without human intervention
Trakt MCP Tools for OpenAI Agents SDK (18)
These 18 tools become available when you connect Trakt to OpenAI Agents SDK via MCP:
get_calendar
Scope can be "my" (user's watched shows) or "all" (all shows). Returns episodes with air dates, times and show info. Get upcoming episode calendar
get_collection
Requires OAuth access token. Returns collected items with metadata and media info. Get the authenticated user's collection
get_history
Requires OAuth access token. Optionally filter by type and ID. Get the authenticated user's watch history
get_movie
Returns title, year, overview, runtime, rating, genres, languages, certification, trailer and poster URLs. Get detailed info for a specific movie
get_movie_people
Each person includes their name, Trakt ID, character name (for cast) and job title (for crew). Get cast and crew for a specific movie
get_movie_ratings
Returns total ratings, average score and the count of votes for each rating level. Get ratings distribution for a specific movie
get_popular
Popularity is based on overall engagement and activity. Returns paginated results. Get the most popular movies or shows
get_related_movies
Each related movie includes title, year, overview, rating and poster URL. Get movies related to a specific movie
get_related_shows
Each related show includes title, year, overview, rating and poster URL. Get shows related to a specific TV show
get_show
Returns title, year, overview, status, runtime, rating, genres, network, certification, trailer and poster URLs. Get detailed info for a specific TV show
get_show_episodes
Each episode includes episode number, title, overview, runtime, ratings and first aired date. Get all episodes for a specific season of a TV show
get_show_people
Get cast and crew for a TV show
get_show_ratings
Returns total ratings, average score and vote counts per rating level. Get ratings distribution for a TV show
get_show_seasons
Each season includes season number, episode count, air date, rating and overview. Get all seasons for a TV show
get_trending
Trending is based on what users are actively watching and checking in. Returns items with viewer counts. Get currently trending movies or shows
get_watched
Requires OAuth access token. Returns items with play counts and last watched timestamps. Get the authenticated user's watched history
get_watchlist
Requires an OAuth access token. Returns movies and/or shows the user has added to their watchlist. Get the authenticated user's watchlist
search
Returns results with titles, years, ratings, genres, IDs and synopsis. Use type parameter to narrow results: "movie", "show", "episode", "person" or "list". Search for movies, shows, episodes, people or lists on Trakt
Example Prompts for Trakt in OpenAI Agents SDK
Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Trakt immediately.
"What movies are trending right now?"
"Show me info about Breaking Bad."
"Who directed The Matrix and who starred in it?"
Troubleshooting Trakt MCP Server with OpenAI Agents SDK
Common issues when connecting Trakt to OpenAI Agents SDK through the Vinkius, and how to resolve them.
MCPServerStreamableHttp not found
pip install --upgrade openai-agentsAgent not calling tools
Trakt + OpenAI Agents SDK FAQ
Common questions about integrating Trakt MCP Server with OpenAI Agents SDK.
How does the OpenAI Agents SDK connect to MCP?
MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.Can I use multiple MCP servers in one agent?
MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.Does the SDK support streaming responses?
Connect Trakt with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Trakt to OpenAI Agents SDK
Get your token, paste the configuration, and start using 18 tools in under 2 minutes. No API key management needed.