Ryot MCP Starter
A local MCP server for interacting with a self-hosted Ryot instance, enabling management of workouts, body measurements, media (movies, shows, games), and collections through natural language.
README
Ryot MCP Starter
A local/private MCP server for a self-hosted Ryot instance, focused on workouts/routines, body measurements, movies, shows, and games.
Project layout
src/
index.ts # MCP bootstrap only
ryot.ts # GraphQL client + live schema helpers
schemas.ts # Shared zod schemas/enums
common.ts # Shared helpers
discovery-tools.ts # Schema/debug/discovery tools
workout-tools.ts # Fitness, measurements, routine tools
media-tools.ts # Movies, shows, games, collections, progress tools
media-convenience-tools.ts # Search-and-act, next-episode, collections, raw review helpers
Configure Cursor/Claude
{
"mcpServers": {
"ryot": {
"command": "node",
"args": ["/absolute/path/to/ryot-mcp-starter/dist/index.js"],
"env": {
"RYOT_BASE_URL": "https://ryot.shivansh.top",
"RYOT_AUTH_HEADER": "Bearer YOUR_RYOT_API_TOKEN",
"RYOT_COOKIE": "",
"RYOT_USER_ID": "",
"RYOT_MOVIE_WATCHLIST_COLLECTION": "Movie Watchlist",
"RYOT_SHOW_WATCHLIST_COLLECTION": "Show Watchlist",
"RYOT_GAME_BACKLOG_COLLECTION": "Game Backlog",
"RYOT_WALKING_EXERCISE_ID": "",
"RYOT_SIT_TO_STAND_EXERCISE_ID": "",
"RYOT_WALL_PUSHUP_EXERCISE_ID": ""
}
}
}
}
RYOT_AUTH_HEADER should contain the exact working Authorization value. For Ryot integration tokens this is usually Bearer <token>.
RYOT_USER_ID is only needed for collection tools such as adding a movie to watchlist or a game to backlog.
Build
npm install
npm run build
Restart Cursor/Claude after every rebuild.
Tools
Core/debug
ryot_health_checkryot_graphqlryot_schema_searchryot_find_candidate_operationsryot_workout_discoveryryot_media_discoveryryot_game_discovery
Fitness/routines
ryot_search_exercisesryot_list_recent_workoutsryot_list_workout_templatesryot_get_workout_detailsryot_get_workout_template_detailsryot_log_workoutryot_create_workout_templateryot_log_body_measurementryot_log_walkryot_log_bodyweight_setryot_log_minimum_workoutryot_create_minimum_routine_templateryot_start_today_routineryot_log_weightryot_log_waistryot_list_measurementsryot_log_minimum_dayryot_log_recovery_dayryot_get_weekly_workout_summary
General media
ryot_search_mediaryot_get_metadata_detailsryot_get_user_metadata_detailsryot_mark_media_progressryot_create_collectionryot_add_to_collectionryot_list_collectionsryot_collection_contentsryot_user_metadata_listryot_create_default_collectionsryot_create_or_update_reviewryot_delete_review
Movies
ryot_search_movieryot_get_movie_statusryot_mark_movie_in_progressryot_mark_movie_watchedryot_add_movie_to_watchlistryot_search_and_mark_movie_watchedryot_search_and_add_movie_to_watchlist
Shows
ryot_search_showryot_get_show_statusryot_mark_show_in_progressryot_mark_show_episode_startedryot_mark_show_episode_watchedryot_add_show_to_watchlistryot_search_and_add_show_to_watchlistryot_search_and_mark_show_episode_watchedryot_get_next_show_episoderyot_mark_next_show_episode_watched
Games
ryot_search_gameryot_get_game_statusryot_mark_game_startedryot_mark_game_completedryot_mark_game_droppedryot_mark_game_on_holdryot_update_game_progress_percentryot_add_game_to_backlogryot_search_and_start_gameryot_search_and_update_game_progressryot_search_and_mark_game_completedryot_search_and_add_game_to_backlog
Notes
Ryot list/search endpoints often return a cached response object rather than full objects directly. This MCP uses live schema introspection to build valid GraphQL selections for object return types, so it should return whatever scalar/cached fields your Ryot version exposes without hard-coding wrapper field names.
For workout logging/templates, Ryot requires internal exerciseId values. Use ryot_search_exercises first, then pass those IDs to ryot_log_workout or set default exercise IDs in env vars.
The high-level routine shortcuts can read default exercise IDs from env vars:
RYOT_WALKING_EXERCISE_IDRYOT_SIT_TO_STAND_EXERCISE_IDRYOT_WALL_PUSHUP_EXERCISE_ID
The collection shortcut tools can read default collection names from env vars:
RYOT_MOVIE_WATCHLIST_COLLECTIONRYOT_SHOW_WATCHLIST_COLLECTIONRYOT_GAME_BACKLOG_COLLECTION
The ryot_search_and_* tools are best-effort wrappers: if Ryot returns only a cached search ID and no metadata ID, they return the search response so you can pick the result and call the ID-based tool.
Review tools are intentionally raw until the exact CreateOrUpdateReviewInput for your Ryot version is confirmed with schema discovery.
Keep this MCP private/local. The generic ryot_graphql tool can run arbitrary queries/mutations against your Ryot account.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。