Rhylthyme
Server Details
Real-time multi-track schedules for cooking, lab protocols, events and workouts. Validate and share.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- rhylthyme/rhylthyme-mcp
- GitHub Stars
- 0
- Server Listing
- Rhylthyme MCP Server
- ChatGPT
- –
- Claude
- Rhylthyme
TDQS
Scored across 20 tools
Most tools are distinct, but three timeline-output tools (preview_timeline, publish_timeline_image, visualize_schedule) overlap in producing a Gantt/URL and differ mainly in publication semantics. The quartet validate_program / analyze_schedule / review_program / calibrate_program also sits close together, though descriptions do draw reasonably clear lines.
Almost the entire set follows a consistent snake_case verb_noun pattern (load_program, list_runs, validate_program, import_from_source, publish_timeline_image). The only real deviation is the bare verb `login`, which breaks the noun-object pattern but is still readable.
At 20 tools the surface is on the heavy side for the apparent scope; pairs like list_runs/list_public_runs and preview_timeline/publish_timeline_image could plausibly be merged. Each tool is individually defensible, but the count sits in the 'borderline heavy' band.
The domain is well covered: import, save/load/list, validate, review, calibrate, analyze, visualize, and run history are all present. The main gap is the absence of any delete operation for programs or runs (and only create_ for environments), which leaves some lifecycle dead ends.
Available Tools
20 toolsanalyze_scheduleAnalyze schedule timingARead-onlyIdempotentInspect
Put a program on the clock: each step's start and end, total length, the critical path and what gates it, resource conflicts, slack per track. Pass finishAt to answer 'when do I start X so everything is ready at 6pm?'. Pure computation. With history (run records) or program_id it also predicts durations from recorded runs.
Inputs: program (required), token, history, startAt, +4 more. Returns: name, steps, tracks, inFlight, +15 more
calibrate_programPropose durations from recorded runsARead-onlyIdempotentInspect
Propose durations for a saved program from its recorded runs: median as the default, P10 to P90 as the range, at least as wide as the author's, with the evidence per step and the effect on total length. Saves nothing; with accept it returns the calibrated program. Needs the user's Rhylthyme account.
Inputs: k, since, token, accept, +3 more.
create_environmentDefine equipment limitsBRead-onlyIdempotentInspect
Describe a workspace's equipment limits (one oven, two centrifuges, one stage) as resourceConstraints to copy into a program, so steps that share equipment are scheduled around each other.
Inputs: name (required), type (required), resourceConstraints (required), actors, +1 more.
get_renderer_sourceGet timeline renderer sourceARead-onlyIdempotentInspect
Return the open-source timeline renderer's JavaScript (Apache-2.0, about 90 KB, no dependencies) for an HTML page or artifact that cannot load external scripts; it defines Rhylthyme.renderTimeline(container, program).
Inputs: no named parameters.
import_from_sourceImport from an external sourceARead-onlyIdempotentInspect
Import a recipe, protocol or run of show into a program. source: spoonacular, themealdb (recipes); protocolsio, opentrons, benchling (lab); cooklang (.cook URL); ontime (run of show). action: search (no account needed), import (query = URL or id), random. import, random and benchling need the user's Rhylthyme account. enrich: true splits an import into parallel tracks. Returns the program.
Inputs: action (required), source (required), text, query, +2 more.
import_textImport pasted textARead-onlyIdempotentInspect
Turn pasted text (a recipe, protocol, run sheet or training plan) into a validated multi-track program on the server, in four model turns, with a table of the source span each step came from. Capped per day. Needs the user's Rhylthyme account.
Inputs: text (required), environmentType (required), hints, token, +1 more.
list_my_programsList my saved programsBRead-onlyIdempotentInspect
List the user's saved programs. Needs the user's Rhylthyme account.
Inputs: token.
list_public_runsList contributed runsARead-onlyIdempotentInspect
List anonymous runs other people contributed for one exact program version: actual against planned length, and their conditions. For 'how long does this really take?'. No account needed. Takes program or program_hash.
Inputs: limit, program, program_hash.
list_runsList recorded runsARead-onlyIdempotentInspect
List recorded runs of a saved program: when, how it ended, actual against planned length. For 'how long did this take last time?'. Needs the user's Rhylthyme account.
Inputs: program_id (required), token.
load_programOpen a saved programARead-onlyIdempotentInspect
Open one of the user's saved programs by id: summary plus live-timeline URL. Needs the user's Rhylthyme account.
Inputs: program_id (required), token.
load_public_recipeOpen a public programARead-onlyIdempotentInspect
Open a public catalog entry by id: summary plus live-timeline URL.
Inputs: program_id (required).
load_runOpen a recorded runARead-onlyIdempotentInspect
Open one recorded run: planned against actual timing per step, what ended each step, pauses. Shows where a plan drifts. Needs the user's Rhylthyme account.
Inputs: run_id (required), token.
loginConnect Rhylthyme accountARead-onlyIdempotentInspect
For apps that cannot connect the Rhylthyme account directly: returns a sign-in URL, then accepts the pasted token. Only the user's own saved programs, runs and imports need it; everything public works without. Tokens last about an hour.
Inputs: token.
preview_timelinePreview timeline imageARead-onlyIdempotentInspect
Return a static Gantt image of a program with a caption, for 'show me a preview' or 'a picture of the timeline'. Publishes nothing. Planned versus actual: with run (a run record) it draws the actual bars over the plan.
Inputs: program (required), run.
publish_timeline_imagePublish timeline imageADestructiveInspect
Publish a program's static Gantt image at a public share link and return the image URL, for a client that can't display images in tool results or a person who wants a link to the picture. This puts a public copy of the program online that the person can't remove. Validates first and refuses an invalid program.
Inputs: program (required). Returns: url, shareId, imageUrl
review_programReview an imported programARead-onlyIdempotentInspect
A model reads an imported program against its source and reports what looks wrong: a default duration on "simmer for an hour", a step the importer dropped, steps chained that could overlap, a total that disagrees with the source. Changes nothing; returns findings to show the user. Needs the user's Rhylthyme account.
Inputs: program (required), token, source_url, source_text.
save_programSave to my accountADestructiveIdempotentInspect
Save a program to the user's account ('save this for later'); the same programId updates it. Needs the user's Rhylthyme account.
Inputs: program (required), token.
search_public_recipesSearch the public catalogARead-onlyIdempotentInspect
Search the public catalog of recipes, lab protocols, event templates and workouts by name or keyword. Returns ids, names, descriptions and URLs; no account needed.
Inputs: limit, query, environment. Returns: count, query, results, environment
validate_programValidate a programARead-onlyIdempotentInspect
Check a program before publishing or saving it: ids, dangling or cyclic triggers, steps overlapping in a track, tasks with no resourceConstraint, durations, replicates/instances misuse. Every finding has a code, a message and a suggested fix. Pure computation.
Inputs: program (required). Returns: info, stats, valid, errors, +1 more
visualize_schedulePublish a live timelineADestructiveInspect
Publish a program as a live, shareable timeline (a public share link) and return its URL, with an ASCII Gantt and an itinerary. For a schedule the user wants to follow or share ('plan this so it all finishes at 6', 'when do I start each thing'). Validates first and refuses an invalid program with fix hints.
Inputs: program (required), allowInvalid. Returns: url, shareId, imageUrl, warnings, +1 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Plan a meal and run kitchen timers that ring on your phone. No sign-in.
Shareable timer links for countdowns, clock times, Pomodoro, Tabata and step recipes. No account.
Create a live, shareable day-of schedule for weddings, shoots, conferences and events.
Shared countdown timers that stay in sync on every screen — no account, any number of viewers.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceCoordinates meal plans, shared kitchen resources like cook/oven/hob, and cook handoffs; supports starting/completing steps, previewing timing changes before applying, undo, and state persistence via MCP.MIT
- AlicenseAqualityBmaintenanceEnables an assistant to watch a cooking video once and then guide a hands-free cook through it: importing videos into validated step-by-step guides, navigating steps, searching timestamped transcript and on-screen evidence, showing exact frames and clip replays, and setting persistent timers across restarts. Sessions, progress, and deadlines are stored so users can resume where they left off.5MIT
- AlicenseNot gradedqualityCmaintenanceEnables agents to create and persist meal plans, track parallel timers and progress, recover from interruptions or constraint changes, and inspect revised schedules through MCP tools.MIT
- AlicenseNot gradedqualityCmaintenanceEnables a voice assistant to backward-plan a multi-dish, multi-cook dinner from serve time, hand each cook their next job, and track progress by voice. When a dish runs late, it re-solves the entire landing — reassigning cooks, compressing steps, and reporting an honest projected serve time rather than hiding the slip.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.