rewind-mcp-server

Check the health and sync status of the Rewind API. Returns API status and last sync times for each data domain.

Get the track currently playing (or most recently scrobbled) on Last.fm. Returns track + artist + album, album cover image, and Apple Music resource link.

Get recently scrobbled tracks from Last.fm, with top-N album covers and Apple Music resource links. Supports date filtering.

Get overall listening statistics from Last.fm including total scrobbles, unique artists, albums, tracks, and daily average. Supports date filtering.

Get top listened-to artists for a time window, with top-N artist images and Apple Music links. Use `period` for vague-recent queries ("lately", "this week") — defaults to \'1month\' (rolling 28 days). Use `date`/`from`/`to` for calendar queries ("in February", "last month", "this year") — date filter overrides period when both are supplied. In MCP Apps hosts, renders an interactive artist portrait grid inline.

Get top listened-to albums from Last.fm for a given time period, with top-N covers and Apple Music links. In MCP Apps hosts, renders an interactive album cover grid inline.

Top listened-to tracks for a time window, with top-N Apple Music links. Optional `artist_id` or `artist_name` filters to a single artist\'s catalog — useful for \'what X songs have I been listening to lately\' queries. Use `period` for vague-recent queries ("lately", "this week") — defaults to \'1month\' (rolling 28 days). Use `date`/`from`/`to` for calendar queries ("in February", "last month", "this year") — date filter overrides period when both are supplied. In MCP Apps hosts, renders an interactive top-tracks card with a List | By album toggle.

Get listening streak data from Last.fm -- current consecutive days with scrobbles and the longest streak ever.

Detailed listening profile for one artist: stats, rank, top tracks and albums, similar artists, and a yearly play sparkline. Includes bio, first/last played, and total scrobbles. Use for natural-language queries like 'tell me about my X listening history'. In MCP Apps hosts, renders an interactive artist card inline.

Get detailed information about a specific album by ID: artist, play count, track listing, cover art, and Apple Music link.

Get genre breakdown over time from Last.fm listening history, grouped by week/month/year. Designed for stacked chart visualization.

Get recently watched movies and TV shows from Plex and Letterboxd. Returns titles, ratings, watch dates, top-N posters, and Letterboxd review links where available. In MCP Apps hosts, renders an interactive poster grid inline.

Get detailed information about a specific movie by ID, including director, genres, rating, summary, watch history, poster image, and Letterboxd review links for rated watches.

Get overall watching statistics including total movies, watch time, movies this year, top genre, top director, TV show counts, and episode counts. Supports date filtering.

Browse the movie collection with filters for genre, decade, director, and year. Supports sorting, pagination, and returns top-N posters.

Get genre breakdown across all watched movies. Returns each genre with movie count and percentage of total watches.

Get decade breakdown across all watched movies. Returns each decade with movie count.

Get top directors by watched-movie count. Returns directors ranked by how many of their films you have watched.

Search across all domains (listening, running, watching, collecting, reading). Three ranking modes: keyword (default) uses FTS5 full-text search across all domains; semantic uses Voyage AI embeddings for paraphrased / meaning-based recall (reading domain only); hybrid fuses both (reading domain only). Use semantic or hybrid when the user describes what an article was ABOUT rather than quoting its words. **Prefer `mode: hybrid` whenever the user mixes a topic with a recalled keyword or a publisher hint** ("the ESPN piece about Ichiro", "the WSJ article on EVs") — semantic alone does not see source domains and can drop the publisher signal entirely. When a result is the article the user is asking about, follow up with `get_article(id)` to render the rich inline article card — do not stop at the search-result text response.

Semantic search over the reading domain using Voyage AI embeddings. Use when the user describes the gist or topic of an article they remember rather than quoting exact words — e.g. "article about a former SNL writer" or "piece about tech layoffs". Returns articles ranked by cosine similarity with a score in [0,1]. Reading domain only. **Important: this tool does NOT see source domains** — embeddings only encode title + description + body. If the user mentions a publisher (ESPN, NYT, WSJ, Atlantic, etc.) or a recalled keyword, prefer `search(mode: "hybrid", ...)` so FTS picks up that signal. **If the top scores cluster within ~0.03 of each other, raise `limit` to 15+** — the right match may sit at position 6+ and approximate-nearest-neighbor noise can swap items at the boundary. When the top result is the article the user is asking about, follow up with `get_article(id)` to render the rich inline article card; if the top score is low (~0.4 and below) or you are unsure which match is right, list the top 2-3 candidates and ask the user to disambiguate before rendering.

Get the unified activity feed across all domains. Returns a chronological list of recent activities (listens, runs, watches, reads, collection adds). Supports date filtering.

Get historical 'on this day' items -- what happened on a given date in previous years across all domains. Defaults to today. Great for nostalgia and reflection.

Fetch one saved article by id, returning its full body, metadata, and highlights. **Use this whenever the user asks what an article says, wants a summary, asks about a specific passage, or needs content past the first ~3000 chars of excerpt.** Also use this as the natural follow-up after `search` / `semantic_search` / `find_similar_articles` / `get_recent_reads` — those return ids; this turns the id into the rich article card. The full body is HTML-stripped plain text (typically 5-30 KB), cached even for paywalled sources (NYT, WSJ, Atlantic, ESPN, etc.) — do NOT fall back to web search or web fetch for article content.

Get recently saved articles from Instapaper. Returns title, author, domain, read time, status, top-N site images where available, and article URLs as resource links. In MCP Apps hosts, renders an interactive article card list inline.

Get saved highlights from Instapaper articles. Returns the highlighted text, notes, source article, and article URLs as resource links.

Get a single random highlight from saved Instapaper articles. Great for daily inspiration or reflection.

Get overall reading statistics from Instapaper including total articles, finished count, currently reading, highlights, and word count.

Find articles thematically similar to a given article by cosine similarity over Voyage AI embeddings. Use after an article has been surfaced (via search, get_recent_reads, or an @rewind://article/{id} mention) when the user asks "what else was I reading like that" or "show me related pieces". No Voyage API call is made — the article\'s stored vector is reused.

Get recent running activities from Strava. Returns runs with ID, distance, pace, duration, location, and Strava activity resource links for top-N.

Browse the vinyl record collection from Discogs. Returns records with artist, title, year, format, and label, plus top-N cover art and Discogs resource links. Supports search, filters, sort, and pagination.

Get overall collection statistics including total items, format breakdown (vinyl, CD, cassette), unique artists, genre data, and year range. Supports date filtering.

Browse the physical media collection (Blu-ray, 4K UHD, HD DVD). Search by title, filter by format. Returns top-N cover art and pagination.

Get statistics for the physical media collection including total items and breakdown by format (Blu-ray, 4K UHD, HD DVD).

List events you bought tickets for: sports games, concerts, theater. Filterable by category (sports/music/arts), event_type (mlb_game, concert, etc.), season, year, venue, and team. Includes events you bought tickets for but did not attend (attended=false). Use `team` (substring match like "mariners" or "huskies") for natural-language queries; `team_id` for stable integer-keyed lookups. When the user asks about a SINGLE specific event ("last Mariners game I went to", "the Springsteen show I attended"), call this with the appropriate filter + `limit: 1` to find the id, then follow up with `get_attended_event(id)` to render the rich inline card — do not stop at the list-tool text response.

Get every game you attended (or hold tickets for) in a given league + season, with W/L record. league is a slug like "mlb", "nfl", "ncaaf", "nba", "wnba". In MCP Apps hosts, renders an interactive season grid with score, attendance, and notable performers.

Search the list of players (MLB, NFL, NCAAF, NBA, etc.) you have watched play in person. Use `name` (substring, case-insensitive) to resolve a player by name. Use `league` and/or `team_id` to filter further. Common names like "Will Smith" return multiple matches — disambiguate via `primary_team.abbreviation` and `primary_position` on each result without a follow-up turn. When the user asks about a SPECIFIC player ("how\'s JP Crawford playing this year", "what are Cal Raleigh\'s stats", "tell me about Kirby"), call this to resolve the name to an id, then follow up with `get_attended_player(id)` to render the rich inline athlete card with current-season stats — do not stop at the search-result text response.

Detailed athlete card for an MLB / NFL / NCAAF / NBA player you\'ve watched play in person. **Use this whenever the user asks how a specific player is performing this season, what their batting average / ERA / current stats are, how their career has gone, or how they\'ve played in the games you attended** — e.g. "how\'s JP Crawford playing this year", "what are Cal Raleigh\'s numbers", "show me Kirby\'s stats", "tell me about Julio Rodriguez". Returns bio (position, jersey, debut, height/weight, college, awards), team logo, current-season stats (live MLB Stats API for MLB players, KV-cached 1h), career-by-season table, home/away/L-R splits, the **season_attended_summary** (this player\'s line in only the games you attended this season — use this to answer "how has he done in the games I\'ve been to this year"), the **attended_summary** (career line across every game you\'ve ever seen this player in), and the 10 most recent attended appearances. Trust season_attended_summary.games_attended as the count of games you\'ve attended this season — do NOT derive it by filtering attended_appearances yourself; that array is capped at 10 most-recent and will undercount for players you see often. MLB-only for the live-stats panel — non-MLB players surface as supported:false. In MCP Apps hosts, renders the rich inline athlete card. If you do not have the player id, first call `get_attended_players` with `name` to resolve the id, then call this to render the card.

Aggregate stats for one player across the games you attended. MLB players get a hitter slash line + counting stats, or a pitcher line + ERA / WHIP / decisions, depending on which stat lines exist on their appearances. Non-MLB players (NFL, NCAAF, NBA, etc.) return supported=false with appearance summaries (final scores, opponents) — full stat-line parsing for those leagues is on the roadmap. \n\n**Use career (omit `season`) by default.** Single-season slices are tiny — max 50 PAs across the entire dataset; career is where meaningful samples live (Cal Raleigh ~130 PAs / 32 attended games; Kirby ~238 BFs / 10 attended starts). Always cite `pa` (hitter) or `bf` (pitcher) and `games` when phrasing the answer so the user can judge confidence.

Aggregate counts of attended events broken down by category, event_type, and year.

Get a single attended event (sports game, concert, theater show) in full detail, including venue, tickets, and per-player stat lines for sports games. Renders the rich inline event card — linescore, top performers with photos, ticket info — in MCP Apps hosts. Use this when the user asks about ONE specific event: "tell me about my last Mariners game," "who pitched in that Phillies game," "the Springsteen show I went to," "what happened at that game." If you do not have the event id, first call `get_attended_events` with a `team` / `event_type` filter (and `limit: 1` if the user asked for the most recent) to find the id, then call this to render the card.

Year-in-review summary for attended events: totals, monthly breakdown, top venues, top concert performers, and the full event list. Use this when the user asks "what shows did I see in 2024" or "best year for games".

Get overall running statistics from Strava including total runs, distance, elevation, duration, average pace, and Eddington number.

Get personal running records (PRs) from Strava -- fastest times at standard distances like mile, 5K, 10K, half marathon, marathon.

Get running streak data from Strava -- current consecutive days with runs and the longest streak ever.

Get detailed information about a specific running activity by ID, including distance, pace, heart rate, elevation, calories, and a Strava resource link.

Get per-mile splits for a running activity. Shows pace, elevation, and heart rate for each mile. Get the activity ID from get_recent_runs.

Get per-year summary of running activity: total runs, distance, elevation, duration, average pace, longest run, and race count for every year on record.