MCP server for human-executed, resource-constrained schedules: validate, analyze
MCP server for human-executed, resource-constrained schedules: validate, analyze, import and publish live timelines on rhylthyme.com. Source of mcp.rhylthyme.com.
active Production-safe Score 94/100 http no auth
At a glance
| Endpoint | https://mcp.rhylthyme.com/gym/mcp |
|---|---|
| Source | https://github.com/rhylthyme/rhylthyme-mcp |
| Transport | http |
| Tools | 22 |
| Auth | none |
| First seen | 2026-10-05 22:54:38 |
| Last checked | 2026-11-17 21:48:33 |
Observed reliability
| 7-day uptime | 100% |
|---|---|
| 24-hour uptime | 100% |
| Handshake success | 100% |
| Latency p50 / p95 | 412 / 857 ms |
| Last successful check | 2026-11-17 21:48:33 |
Measured by Arclan's validator via repeated live MCP handshakes. How this is computed →
Tools (22)
validate_program— Check a program before publishing or saving it: ids, dangling or cyclic triggers, steps overlapping in a track, tasks with no resourceConstranalyze_schedule— 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 tracvisualize_schedule— 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 workouimport_from_source— Import a recipe, protocol or run of show into a program. source: spoonacular, themealdb (recipes); protocolsio, opentrons, benchling (lab);import_text— Turn pasted text (a workout) into a validated multi-track program on the server, in four model turns, with a table of the source span each screate_environment— Describe a workspace's equipment limits (one oven, two centrifuges, one stage) as resourceConstraints to copy into a program, so steps thatlogin— For apps that cannot connect the Rhylthyme account directly: returns a sign-in URL, then accepts the pasted token. Only the user's own savedlist_my_programs— List the user's saved workouts. Needs the user's Rhylthyme account.load_program— Open one of the user's saved workouts by id: summary plus live-timeline URL. Needs the user's Rhylthyme account.list_runs— List recorded runs of a saved workout: when, how it ended, actual against planned length. For 'how long did this take last time?'. Needs thereview_program— A model reads an imported workout against its source and reports what looks wrong: a default duration on "simmer for an hour", a step the imload_run— Open one recorded run: planned against actual timing per step, what ended each step, pauses. Shows where a plan drifts. Needs the user's Rhycalibrate_program— Propose durations for a saved workout from its recorded runs: median as the default, P10 to P90 as the range, at least as wide as the authorlist_public_runs— List anonymous runs other people contributed for one exact workout version: actual against planned length, and their conditions. For 'how losearch_public_recipes— Search the public catalog of workouts by style, body part or modality. Returns ids, names, descriptions and URLs; no account needed.load_public_recipe— Open a public workout by id: summary plus live-timeline URL.save_program— Save a workout to the user's account ('save this for later'); the same programId updates it. Needs the user's Rhylthyme account.preview_timeline— Return a static Gantt image of a program with a caption, for 'show me a preview' or 'a picture of the timeline'. Publishes nothing. Plannedpublish_timeline_image— 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 resulget_renderer_source— Return the open-source timeline renderer's JavaScript (Apache-2.0, about 90 KB, no dependencies) for an HTML page or artifact that cannot lostart_workout— Find the best public workout for a keyword and return its live timeline in one call, for requests like 'let's do HIIT', 'push day workout'.surprise_workout— Pick a random public workout and return its live timeline, for requests like 'pick a workout for me'.
Validation history
| Checked | Reachable | Handshake | Latency | Score | State |
|---|---|---|---|---|---|
| 2026-11-17 21:48:33 | ✓ | ✓ | 223 ms | 94 | active |
| 2026-11-17 21:33:27 | ✓ | ✓ | 476 ms | 91 | active |
| 2026-11-17 21:18:17 | ✓ | ✓ | 326 ms | 91 | active |
| 2026-11-17 21:03:13 | ✓ | ✓ | 222 ms | 94 | active |
| 2026-11-17 20:47:55 | ✓ | ✓ | 367 ms | 91 | active |
| 2026-11-17 20:32:48 | ✓ | ✓ | 321 ms | 91 | active |
| 2026-11-17 20:17:45 | ✓ | ✓ | 449 ms | 91 | active |
| 2026-11-17 20:02:10 | ✓ | ✓ | 215 ms | 94 | active |
| 2026-11-17 19:46:50 | ✓ | ✓ | 500 ms | 91 | active |
| 2026-11-17 19:31:46 | ✓ | ✓ | 376 ms | 91 | active |
| 2026-11-17 19:16:38 | ✓ | ✓ | 278 ms | 94 | active |
| 2026-11-17 19:00:58 | ✓ | ✓ | 447 ms | 91 | active |
| 2026-11-17 18:45:56 | ✓ | ✓ | 569 ms | 91 | active |
| 2026-11-17 18:30:55 | ✓ | ✓ | 234 ms | 94 | active |
| 2026-11-17 18:15:52 | ✓ | ✓ | 564 ms | 91 | active |
Query this programmatically
Agents can pull this record live over the MCP protocol or REST:
get_server("https://mcp.rhylthyme.com/gym/mcp") # via the Arclan MCP endpoint https://arclan.ai/mcp
GET https://arclan.ai/api/registry/mcp-rhylthyme-com-gym-mcp # JSON