Trakt

77 tools. 14 can modify or destroy data without limits.

5 destructive tools with no built-in limits. Policy required.

Last updated:

14 can modify or destroy data
63 read-only
77 tools total

Community server · catalogue entry verified 11/06/2026

How to control Trakt ↓

Read (63) Write / Execute (9) Destructive / Financial (5)
Critical Risk

14 of Trakt's 77 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

PolicyLayer is an MCP gateway — it sits between your AI agents and Trakt, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations
{
  "clear_auth": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations
{
  "checkin_to_show": {
    "limits": [
      {
        "counter": "checkin_to_show_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "check_auth_status": {
    "limits": [
      {
        "counter": "check_auth_status_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

  1. Create a free account and register Trakt — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON TRAKT →

Free to start. No card required.

READ 63 tools
Read check_auth_status Check the status of an ongoing device authentication flow Read fetch_anticipated_movies fetch_anticipated_movies Read fetch_anticipated_shows fetch_anticipated_shows Read fetch_boxoffice_movies fetch_boxoffice_movies Read fetch_comment Fetch a specific comment from Trakt Read fetch_comment_replies fetch_comment_replies Read fetch_episode_comments fetch_episode_comments Read fetch_episode_lists Fetch lists that contain a specific TV show episode. Read fetch_episode_people fetch_episode_people Read fetch_episode_ratings fetch_episode_ratings Read fetch_episode_stats fetch_episode_stats Read fetch_episode_summary fetch_episode_summary Read fetch_episode_translations fetch_episode_translations Read fetch_episode_videos fetch_episode_videos Read fetch_episode_watching fetch_episode_watching Read fetch_favorited_movies fetch_favorited_movies Read fetch_favorited_shows fetch_favorited_shows Read fetch_history fetch_history Read fetch_movie_comments fetch_movie_comments Read fetch_movie_people fetch_movie_people Read fetch_movie_ratings Fetch ratings and voting statistics for a specific movie Read fetch_movie_recommendations fetch_movie_recommendations Read fetch_movie_summary fetch_movie_summary Read fetch_movie_videos fetch_movie_videos Read fetch_person_lists fetch_person_lists Read fetch_person_movies fetch_person_movies Read fetch_person_shows fetch_person_shows Read fetch_person_summary fetch_person_summary Read fetch_playback_progress fetch_playback_progress Read fetch_played_movies fetch_played_movies Read fetch_played_shows fetch_played_shows Read fetch_popular_movies fetch_popular_movies Read fetch_popular_shows fetch_popular_shows Read fetch_related_movies fetch_related_movies Read fetch_related_shows fetch_related_shows Read fetch_season_comments fetch_season_comments Read fetch_season_episodes fetch_season_episodes Read fetch_season_info fetch_season_info Read fetch_season_lists Fetch lists that contain a specific TV show season. Read fetch_season_people fetch_season_people Read fetch_season_ratings fetch_season_ratings Read fetch_season_stats fetch_season_stats Read fetch_season_translations fetch_season_translations Read fetch_season_videos fetch_season_videos Read fetch_season_watching fetch_season_watching Read fetch_show_comments fetch_show_comments Read fetch_show_people fetch_show_people Read fetch_show_progress fetch_show_progress Read fetch_show_ratings Fetch ratings and voting statistics for a specific TV show Read fetch_show_recommendations fetch_show_recommendations Read fetch_show_seasons fetch_show_seasons Read fetch_show_summary fetch_show_summary Read fetch_show_videos fetch_show_videos Read fetch_trending_movies fetch_trending_movies Read fetch_trending_shows fetch_trending_shows Read fetch_user_ratings fetch_user_ratings Read fetch_user_watched_movies fetch_user_watched_movies Read fetch_user_watched_shows fetch_user_watched_shows Read fetch_user_watchlist fetch_user_watchlist Read fetch_watched_movies fetch_watched_movies Read fetch_watched_shows fetch_watched_shows Read search_movies Search for movies on Trakt by title Read search_shows Search for TV shows on Trakt by title

Other MCP servers with similar tools — same risk classification, starter policies for each.

Can an AI agent delete data through the Trakt MCP server? +

Yes. The Trakt server exposes 5 destructive tools including clear_auth, remove_from_history, remove_playback_item. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Trakt? +

The Trakt server has 8 write tools including checkin_to_show, hide_movie_recommendation, hide_show_recommendation. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Trakt.

How many tools does the Trakt MCP server expose? +

77 tools across 4 categories: Destructive, Execute, Read, Write. 63 are read-only. 14 can modify, create, or delete data.

How do I enforce a policy on Trakt? +

Register the Trakt MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Trakt tool call.

Deterministic rules across all 77 Trakt tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

77 Trakt tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.