MCP App Store
by KeenEthics
ReelRecs icon

ReelRecs MCP Server for Claude and ChatGPT

By REELRECS INC

Overview

Find a movie or show for tonight without doing the homework. Start with ‘Netflix tonight’, ‘something light’ or ‘movies like Get Out’. ReelRecs brings Claude current trending titles, U.S. audience charts, rich title details and streaming options so it can suggest a few appealing choices and refine them from your reactions. Explore similar titles through viewing, rating and theme patterns. Compare audience ReelRecs Scores, watch trailers and open ReelRecs title pages for more details. Public discovery works without a ReelRecs account. Connect your account for saved-taste recommendations, personal Rec Score predictions, your rated-title history, bookmarks and choices for accepted Watch+ groups. Account access is read-only. A short optional reaction or problem report can help improve recommendations, subject to Claude’s permissions.

How to connect

  1. Claude: Open the ReelRecs listing in the Claude connectors directory and choose Connect. Claude listing ReelRecs exposes 13 tools here.
  2. ChatGPT: Open the ReelRecs listing in the ChatGPT app directory and choose Connect. ChatGPT listing ReelRecs exposes 13 tools here.

Tools

get_charts

ChatGPT
Find movies or TV shows for tonight or a mood: "What should I watch?", "Netflix tonight", "Something light", "tense but not depressing", "help me figure out what I'm in the mood to watch", or what's popular on streaming. Start here even when an account is connected. Use mood_preferences to shape the shortlist when the viewer names a feeling, then use viewing_experience and title details to choose. If trending offers too few fitting options, use chart=popular with the same practical constraints. No reference title or preference questionnaire is needed. If the viewer is unsure, give concrete picks in two easy directions and let their reaction guide you; mood is an optional follow-up alongside service and movie-versus-show. Returns up to twelve candidates from the latest available U.S. audience charts, with ReelRecs Score, descriptions, genres, subgenres, tags, keywords, subjects, cast, directors, runtime and links. An authorized connection can also add personal Rec Score predictions to these current choices. Streaming-service filtering uses constraints.providers with constraints.country; country alone does not establish availability. Also supports genre, runtime, first-release-year and exclusion filters. Trending and rising measure attention at chart_as_of; popular measures broader audience demand. chart_freshness and chart_age_days distinguish dated discovery snapshots from current rankings. Chart attention is distinct from new releases, and the chart market is distinct from availability country. Provides movie and series discovery, not live sports fixtures or broadcast schedules. No ReelRecs account required.

get_my_bookmarks

ChatGPT
Use for my bookmarks, my watchlist, saved movies or shows, did I save this title, and help me pick from my list. Lists the connected viewer's own saves, newest first; query searches the full list by title fragment, kind filters movies or shows, and next_offset retrieves another page. Start a simple browse with the default page and a short linked list; show remaining fetched titles before fetching more when requested or when it helps choose. matched_count is the total for the applied filters. If a movie/show breakdown is requested, use kind-filtered counts rather than estimating it. Returns saved dates, descriptions, genres, subgenres, tags, runtime, ReelRecs links and audience scores. With personal recommendation permission, also adds Your Rec Score predictions. Keep picks within the returned bookmarks when requested, check watch options, and curate a few fitting choices using available returned title links. Rated or watched titles can still be bookmarked; do not infer history or likes from a save. Requires bookmarks:read permission. Cannot read another account or add/remove saves.

get_my_profile

ChatGPT
Read account identity and saved streaming-service names when the viewer asks about their account or saved services. This is not a prerequisite for recommendations or help discovering a viewing mood; use public get_charts for those requests. Returns display identity, whether saved taste is available, and streaming_preferences.services, not a taste analysis. get_watch_options also matches offers to these preferences. Requires a connected ReelRecs account. Never exports full history.

get_my_ratings

ChatGPT
Use for my ratings, all the movies and shows I rated, understand my taste, what I loved or disliked, and have I rated this title. Omit title_ids to browse the viewer's full rated list, independently of bookmarks. Browse with an optional title fragment, kind, highest/lowest/title sort, and next_offset; up to 50 titles per page. For a requested full-history taste analysis, read all pages and use both high and low ratings with the returned descriptions, genres, subgenres and tags. Curate a few picks using that evidence; personal predictions are secondary when requested. Alternatively supply up to ten resolved title_ids to check saved ratings or confirmed absence for those specific titles. Requires ratings:read. Saved ratings, audience scores and personal predictions are distinct. A successful lookup confirms the connection. Cannot read another account or change ratings.

get_my_watchplus_groups

ChatGPT
Find the connected viewer's accepted Watch+ groups by group or member name, such as Jenna. Returns current accepted member IDs, display names and app usernames, never emails or pending invitees. Use these IDs for the people watching now, then recommend_for_group. Match usernames to distinguish duplicate names; when the same people share several groups, prefer the smallest matching group unless the viewer names one. Proceed directly when the people are clear. Requires watchplus:read permission.

get_title_peers

ChatGPT
Find optional content references for one resolved movie or show when a comparison is useful. Returns ReelRecs Score out of 10, descriptions, tags, subgenres and links. Candidates are selected from content without audience-score or viewing/rating-affinity selection. They do not represent a shared group of raters, and no peer average is calculated. Missing scores are null. Streaming offers are not included.

get_watch_options

ChatGPT
Country-specific streaming offers for up to ten canonical titles. Subscription, free, ads, rental and purchase are separate. Includes observation dates and availability freshness.

get_watchplus_context

ChatGPT
Explore the selected accepted group members' accessible tastes. Returns liked and less-liked examples and descriptive patterns. Supply up to ten resolved title IDs for each person's predicted rating, saved rating, Watch+ interest/pass and relevant saved references, including evidence beyond the overview examples. Helps explain shared appeal, differences, reservations and compromises. Profiles respect existing privacy and blocks. Missing evidence is unknown. Similar saved titles illustrate content overlap; they do not explain the scoring model's causes. Requires watchplus:read; cannot read strangers, pending invitations, private chats or change anything.

recommend_for_group

ChatGPT
Choose what the accepted Watch+ members watching together might enjoy tonight. Resolve the group and people with get_my_watchplus_groups first. Returns up to twelve compact candidates for the assistant to curate into two or three, with rich title details, audience ReelRecs Score, separate per-person Rec Score predictions, saved ratings, Watch+ votes and related likes/dislikes. Prioritizes balanced fit and current interest by default; focus=all_titles explores the library. Pass votes lower priority without changing predictions. Excludes known seen titles unless allow_rewatch. Send mood_preferences when the viewer expresses a feeling; it orders a wider eligible shortlist using stored mood levels. Keep positive/disliked references and streaming filters when known. If you find alternatives through charts, use get_watchplus_context for those titles and the same people before making group picks. Do not demand a questionnaire or conclude the service has nothing from a thin shortlist. Predictions require fresh completed scores; missing coverage never means agreement. Requires watchplus:read and current accepted membership. Privacy and blocks are checked again before returning.

recommend_for_me

ChatGPT
Use when the viewer asks to explore their saved taste or the wider library, such as "recommend based on my ratings". For an open-ended "Netflix tonight", "What should I watch?" or mood-only start, use get_charts first even when connected; current chart candidates can include personal predictions too. This tool ranks the wider catalogue by saved taste, positive or disliked reference titles and desired qualities. Returns up to twelve candidates with rich title context, audience ReelRecs Score, personal Your Rec Score predictions and links. Both scores use a ten-point scale; missing predictions are null. Weigh personal fit with the viewing experience and tonight's mood. Excludes watched titles unless rewatch is requested and can use saved streaming services. Saved taste describes lasting preferences; the qualities_applied field identifies whether mood text affected ranking. Requires an authorized ReelRecs account and never accepts an account identifier.

recommend_titles

ChatGPT
Find movies like X, shows to watch after Y, or alternatives when someone liked one title but disliked another. Resolve names with search_titles first, then pass positive and disliked reference IDs plus any desired qualities. For open-ended or mood-only discovery without reference titles, use get_charts and choose from its viewing_experience context; this avoids relying on optional free-text encoding. Returns up to twelve candidates with ReelRecs Score, descriptions, genres, subgenres, subjects, tags, keywords, cast, directors, runtime, viewing_experience mood levels, reference overlaps and title links. General similarity supplies the neighborhood; intent selects the supporting evidence emphasis. Dislikes adjust comparable affinities; exclusions hide exact titles. Use mood_preferences for soft ordering by stored feelings, even when qualities_applied says the free-text ranking was unavailable. Provider filters apply in the requested country; country alone does not filter availability. No account required.

report_recommendation_feedback

ChatGPT
Record a brief quality report about a meaningful acceptance, rejection, correction or concrete problem with ReelRecs results, when permitted by the viewer and host. At most one report per new signal across ReelRecs tools. Accepts the relevant result request_id and up to five affected title IDs copied from results when available; otherwise omit them. IDs must not be invented. The paraphrase is limited to 300 characters. User statements, actions and uncertain assistant inferences are separate evidence types; inference confidence must be low or medium. Silence or continued use is not evidence of a reaction. Transcripts, identity, credentials and sensitive personal details are outside the report's scope. Reports are unverified observations and cannot change saved ratings or taste. Returns receipt acknowledgement; host approval controls and viewer opt-out apply.

search_titles

ChatGPT
Find a movie or TV show from its name, a remembered fragment or a typo. Resolve its exact version before recommendations or availability checks. Returns canonical IDs and rich title context: description, genres, subgenres, tags, subjects, keywords, cast, directors, language, runtime and viewing_experience mood levels with scope and evidence labels. Choices cover viewer-mentioned titles or assistant-chosen mood references.

get_charts

Claude
Find trending and popular movies and TV shows to help choose what to watch tonight. Useful for short requests such as "What's good on TV tonight?", "What's popular on streaming?", "What's good on Netflix?" or "Help me pick something". Works with or without saved preferences or a known mood, and does not need a reference title. Returns up to twelve candidates from the latest available U.S. audience charts, with ReelRecs Score, descriptions, genres, subgenres, tags, keywords, subjects, cast, directors, runtime and links. Streaming-service filtering uses constraints.providers with constraints.country; country alone does not establish availability. Also supports genre, runtime, first-release-year and exclusion filters. Trending and rising measure attention at chart_as_of; popular measures broader audience demand. chart_freshness and chart_age_days distinguish dated discovery snapshots from current rankings. Chart attention is distinct from new releases, and the chart market is distinct from availability country. Provides movie and series discovery, not live sports fixtures or broadcast schedules. No ReelRecs account required.

get_my_bookmarks

Claude

get_my_profile

Claude
Requires a connected ReelRecs account. Returns display identity and whether saved taste is available; never exports full history.

get_my_ratings

Claude
Look up saved numeric ratings for up to ten viewer-requested canonical movie or show IDs. Requires a connected account with ratings:read permission. Returns a saved rating or confirmed absence for each requested title. Saved ratings are distinct from predicted scores and watched status. A successful lookup also confirms the connection. Never accepts an account identifier; cannot change ratings.

get_my_watchplus_groups

Claude

get_title_peers

Claude
Find optional content references for one resolved movie or show when a comparison is useful. Returns ReelRecs Score out of 10, descriptions, tags, subgenres and links. Candidates are selected from content without audience-score or viewing/rating-affinity selection. They do not represent a shared group of raters, and no peer average is calculated. Missing scores are null. Streaming offers are not included.

get_watch_options

Claude
Country-specific streaming offers for up to ten canonical titles. Subscription, free, ads, rental and purchase are separate. Includes observation dates and availability freshness.

get_watchplus_context

Claude

recommend_for_group

Claude

recommend_for_me

Claude
Find recommendations based on the connected viewer's saved taste, positive or disliked reference titles and desired qualities. Returns up to twelve candidates with rich title context, ReelRecs Score and links. Excludes watched titles unless rewatch is requested and can use saved streaming services. Saved taste describes lasting preferences; the qualities_applied field identifies whether mood text affected ranking. Requires an authorized ReelRecs account and never accepts an account identifier.

recommend_titles

Claude
Find a shortlist from resolved positive references, disliked references and desired qualities. Useful for more-like-this requests or exploring a particular viewing experience. Returns up to twelve candidates with ReelRecs Score, descriptions, genres, subgenres, subjects, tags, keywords, cast, directors, runtime, reference overlaps and title links. General similarity supplies the neighborhood; intent selects the supporting evidence emphasis. Dislikes adjust comparable affinities; exclusions hide exact titles. The qualities_applied field identifies whether mood text affected ranking. Provider filters apply in the requested country; country alone does not filter availability. No account required.

report_recommendation_feedback

Claude
Record a brief quality report about a meaningful acceptance, rejection, correction or concrete problem with ReelRecs results, when permitted by the viewer and host. At most one report per new signal across ReelRecs tools. Accepts the relevant result request_id and up to five affected title IDs copied from results when available; otherwise omit them. IDs must not be invented. The paraphrase is limited to 300 characters. User statements, actions and uncertain assistant inferences are separate evidence types; inference confidence must be low or medium. Silence or continued use is not evidence of a reaction. Transcripts, identity, credentials and sensitive personal details are outside the report's scope. Reports are unverified observations and cannot change saved ratings or taste. Returns receipt acknowledgement; host approval controls and viewer opt-out apply.

search_titles

Claude
Resolve a title name and optional year to canonical IDs and rich title context: description, genres, subgenres, tags, subjects, keywords, cast, directors, language and runtime. Returns exact-version choices for viewer-mentioned titles or assistant-chosen mood references.

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/reelrecs"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/reelrecs)