Trakt MCP Server
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Trakt MCP Serversearch for 'Inception'"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Trakt MCP Server
A Model Context Protocol (MCP) server for the Trakt.TV API, deployable to Vercel. Connect any MCP-compatible AI agent to your Trakt watch history, ratings, watchlist, and much more.
Features
30+ MCP tools spanning search, movies, TV shows, and user account features
OAuth authentication — users connect their Trakt account via the landing page
No auth required for public tools (search, trending, popular, details)
One-click Vercel deployment with built-in Streamable HTTP transport
Beautiful landing page for OAuth flow and configuration
Related MCP server: TMDB MCP Server
Available Tools
Public (no auth required)
trakt_search— Search for movies, shows, episodes, peopletrakt_lookup— Look up items by IMDb, TMDb, TVDB, or Trakt IDtrakt_get_movie/trakt_get_show— Get full detailstrakt_trending_movies/trakt_trending_showstrakt_popular_movies/trakt_popular_showstrakt_related_movies/trakt_related_showstrakt_movie_people/trakt_show_people— Cast & crewtrakt_get_show_seasons/trakt_get_season_episodes/trakt_get_episodetrakt_anticipated_movies
Requires OAuth (🔒)
trakt_get_profile/trakt_get_statstrakt_get_watchlist/trakt_add_to_watchlist/trakt_remove_from_watchlisttrakt_get_history/trakt_add_to_historytrakt_get_ratings/trakt_add_ratingtrakt_get_watchedtrakt_checkin/trakt_delete_checkintrakt_get_lists/trakt_get_list_itemstrakt_get_calendartrakt_get_recommendations
Setup
1. Create a Trakt App
Go to trakt.tv/oauth/applications and create a new application.
Set the Redirect URI to:
Local:
http://localhost:3000/api/auth/callbackVercel:
https://your-project.vercel.app/api/auth/callback
2. Configure Environment Variables
cp .env.example .env.localEdit .env.local:
TRAKT_CLIENT_ID=your_client_id
TRAKT_CLIENT_SECRET=your_client_secret
NEXT_PUBLIC_BASE_URL=http://localhost:30003. Run Locally
bun install
bun devVisit http://localhost:3000 and click Connect with Trakt to get your access token.
4. Deploy to Vercel
bunx vercelSet environment variables in the Vercel dashboard:
TRAKT_CLIENT_IDTRAKT_CLIENT_SECRET
MCP Client Configuration
Add to your MCP client config (e.g., Cursor, Claude Desktop):
{
"mcpServers": {
"trakt": {
"url": "https://your-project.vercel.app/api/mcp",
"headers": {
"Authorization": "Bearer YOUR_TRAKT_ACCESS_TOKEN"
}
}
}
}For public-only access (no user features), omit the headers block.
Architecture
src/
├── app/
│ ├── api/
│ │ ├── [transport]/route.ts # MCP Streamable HTTP endpoint
│ │ └── auth/callback/route.ts # Trakt OAuth callback
│ ├── .well-known/
│ │ └── oauth-protected-resource/route.ts # OAuth metadata
│ ├── layout.tsx
│ ├── page.tsx # Landing page with OAuth flow
│ └── globals.css
└── lib/
├── mcp-server.ts # MCP server factory
├── tools/
│ ├── search.ts # Search & lookup tools
│ ├── movies.ts # Movie tools
│ ├── shows.ts # TV show tools
│ └── user.ts # User/auth tools
└── trakt/
├── client.ts # API client + error handling
└── types.ts # TypeScript type definitionsThis server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Lorenzo0111/TraktMCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server