corep.stonefish.dev
A local-first fitness tracker you and your AI agent operate together, over WebMCP.
First seen 2026-11-05 · Last seen 2026-11-05 · Source: webmcp.com
Answer 11 · Act 17 · Transact 3 · Score: Not yet scored
Tool inspector
fitness_log_workout
Record a completed workout. `date` defaults to today. For each movement record what was actually done, not what was planned — if they did fewer reps or dropped the weight, log that. Mark anything they skipped with skipped=true and a skip_reason. Put anything that hurt in pain_notes; it surfaces in progress summaries. Returns any badges this unlocks so you can congratulate them.
Input schema
| Property | Type | Required | Description |
|---|---|---|---|
exercises |
array | yes | What was performed. |
date |
string | no | Date of the workout, "YYYY-MM-DD". Defaults to today. |
plan_id |
string | no | The plan this session belongs to, if any. |
block_id |
string | no | The phase this session belongs to, if any. |
mood_after |
integer | no | How they felt afterwards, 1 (bad) to 5 (great). |
energy_before |
integer | no | Energy going in, 1 (flat) to 5 (fresh). |
pain_notes |
string | no | Anything that hurt or felt off. Important — it drives future advice. |
general_notes |
string | no | Any other note about the session. |
Raw JSON schema
{
"type": "object",
"properties": {
"exercises": {
"type": "array",
"items": {
"type": "object",
"properties": {
"exercise_name": {
"type": "string",
"description": "Name of the movement performed."
},
"plan_exercise_id": {
"type": "string",
"description": "The planned exercise this fulfils, when there is one. Links the log to the plan so progress trends work."
},
"actual_sets": {
"type": "integer",
"description": "Sets actually completed."
},
"actual_reps": {
"type": "integer",
"description": "Reps per set actually performed."
},
"actual_weight": {
"type": "number",
"description": "Weight actually used, in pounds (lbs)."
},
"actual_duration": {
"type": "integer",
"description": "Seconds held, for timed movements."
},
"difficulty": {
"type": "integer",
"description": "How hard it felt, 1 (easy) to 5 (maximal)."
},
"skipped": {
"type": "boolean",
"description": "True if the movement was skipped entirely."
},
"skip_reason": {
"type": "string",
"description": "Why it was skipped."
},
"notes": {
"type": "string",
"description": "Any note about this movement in this session."
}
},
"required": [
"exercise_name"
]
},
"description": "What was performed."
},
"date": {
"type": "string",
"description": "Date of the workout, \"YYYY-MM-DD\". Defaults to today."
},
"plan_id": {
"type": "string",
"description": "The plan this session belongs to, if any."
},
"block_id": {
"type": "string",
"description": "The phase this session belongs to, if any."
},
"mood_after": {
"type": "integer",
"description": "How they felt afterwards, 1 (bad) to 5 (great)."
},
"energy_before": {
"type": "integer",
"description": "Energy going in, 1 (flat) to 5 (fresh)."
},
"pain_notes": {
"type": "string",
"description": "Anything that hurt or felt off. Important — it drives future advice."
},
"general_notes": {
"type": "string",
"description": "Any other note about the session."
}
},
"required": [
"exercises"
]
}
Similar websites
pocketgull.app
Pocket Gull is a real-time clinical AI consult engine powered by Google Gemini. Features 10D multi-paradigm strategy, FHIR R4 export & 3D spatial anatomy.
webmcp-six-lac.vercel.app
AI Navigation Layer: Model Context Protocol (MCP) Semantic DOM integration for intelligent, safe, and observable web navigation.
ghqsandbox.net
Interactive math and physics tools an AI agent can drive directly through WebMCP.
app.formative.com
Formative classroom assessment and learning platform