Fitfly Engine

Working · 1.5 s

io.github.dropflyai/fitfly-enginev0.2.0

Deterministic fitness coaching engine: adaptive programs, progression math, readiness autoregulation

Health & Science

Website Registry entry

Maintain this server? Claim it

Try it

Call this server's tools from your browser. Nothing to install.

https://workout-engine-production-5dd7.up.railway.app/mcp

Authorization (required)

Bearer fft_... personal access token. FitFly users mint one via POST /api/engine/me/mcp-token; coaches mint athlete tokens via the partner API. See /connect.

Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.

Tool list from our last check. Connect live to refresh it.

changelog

The 'what changed & why' feed — the engine's coaching decisions (volume bumps, deloads, swaps) in Coach Fly's voice. Use to explain to the athlete why their plan evolved.

limitinteger

This tool isn't marked read-only, so it may change something on the server or in an account you connected.

I understand, run it anyway

Tools (10)

changelog

The 'what changed & why' feed — the engine's coaching decisions (volume bumps, deloads, swaps) in Coach Fly's voice. Use to explain to the athlete why their plan evolved.

Argument	Type	Description
limit	integer

Input schema (JSON)

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991
    }
  }
}

get_program

The athlete's current multi-day program (render-ready).

No arguments.

Input schema (JSON)

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {}
}

get_todays_session

Today's workout: exercises, sets/reps, per-exercise load guidance and concrete target weights, plus nutrition targets and cycle status. Auto-applies the user's readiness check-in (autoregulation) if they've done one today. Call this to see what the athlete should do now.

Argument	Type	Description
dayIndex	integer	Which program day (1-based). Defaults to the first day.

Input schema (JSON)

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "dayIndex": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "description": "Which program day (1-based). Defaults to the first day."
    }
  }
}

list_swap_options

Valid alternatives for an exercise — same muscle group, filtered to the athlete's equipment/level/injuries. Use before swap_exercise.

Argument	Type	Description
exerciseId*	string

Input schema (JSON)

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "exerciseId"
  ],
  "properties": {
    "exerciseId": {
      "type": "string"
    }
  }
}

log_workout

Record what the athlete actually lifted. The engine runs progression (double-progression, e1RM), detects PRs, and returns per-exercise outcomes (established/progressed/held/deloaded) with next-time targets. Weights are in kg.

Argument	Type	Description
goal	string
dayIndex	integer
exercises*	array	Per-exercise completed sets (weights in kg).

Input schema (JSON)

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "exercises"
  ],
  "properties": {
    "goal": {
      "enum": [
        "strength",
        "hypertrophy",
        "general_fitness",
        "fat_loss"
      ],
      "type": "string"
    },
    "dayIndex": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991
    },
    "exercises": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "exerciseId",
          "sets"
        ],
        "properties": {
          "sets": {
            "type": "array",
            "items": {
              "type": "object",
              "required": [
                "weightKg",
                "reps"
              ],
              "properties": {
                "rpe": {
                  "anyOf": [
                    {
                      "type": "number"
                    },
                    {
                      "type": "null"
                    }
                  ]
                },
                "reps": {
                  "type": "integer",
                  "maximum": 9007199254740991,
                  "minimum": -9007199254740991
                },
                "weightKg": {
                  "type": "number"
                },
                "completed": {
                  "type": "boolean"
                }
              }
            }
          },
          "exerciseId": {
            "type": "string"
          },
          "prescribedRepTop": {
            "type": "integer",
            "maximum": 9007199254740991,
            "minimum": -9007199254740991
          }
        }
      },
      "description": "Per-exercise completed sets (weights in kg)."
    }
  }
}

meal_plan

A day of meals hitting the athlete's targets, USDA truth-checked (flags feasible=false with a note when macros are approximate). Slow (~15s AI call).

Argument	Type	Description
exclusions	array
mealsPerDay	integer
trainingDay	boolean
dietaryStyle	string

Input schema (JSON)

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "exclusions": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "mealsPerDay": {
      "type": "integer",
      "maximum": 5,
      "minimum": 3
    },
    "trainingDay": {
      "type": "boolean"
    },
    "dietaryStyle": {
      "type": "string"
    }
  }
}

nutrition_targets

The athlete's daily calorie + macro targets, computed from body stats, activity, and goal.

No arguments.

Input schema (JSON)

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {}
}

readiness_checkin

Record how the athlete feels today (energy, sleep, soreness — each 1–5). The engine scores readiness and, on the next get_todays_session, reshapes the workout accordingly (reduce volume / reduce intensity / recovery day). Returns the readiness score + modifier.

Argument	Type	Description
sleep*	integer	1 terrible … 5 great
energy*	integer	1 drained … 5 great
soreness*	integer	1 none … 5 very sore

Input schema (JSON)

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "energy",
    "sleep",
    "soreness"
  ],
  "properties": {
    "sleep": {
      "type": "integer",
      "maximum": 5,
      "minimum": 1,
      "description": "1 terrible … 5 great"
    },
    "energy": {
      "type": "integer",
      "maximum": 5,
      "minimum": 1,
      "description": "1 drained … 5 great"
    },
    "soreness": {
      "type": "integer",
      "maximum": 5,
      "minimum": 1,
      "description": "1 none … 5 very sore"
    }
  }
}

regenerate_program

Rebuild the whole program from the stored profile (~20s AI generation). Use after a profile change or a plateau.

No arguments.

Input schema (JSON)

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {}
}

swap_exercise

Replace an exercise with a valid same-area alternative. scope 'today' = just this session; scope 'program' = going forward. The new lift starts fresh (day-one calibration).

Argument	Type	Description
scope	string	Default 'program'.
dayIndex	integer
exerciseId*	string
toExerciseId*	string

Input schema (JSON)

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "exerciseId",
    "toExerciseId"
  ],
  "properties": {
    "scope": {
      "enum": [
        "today",
        "program"
      ],
      "type": "string",
      "description": "Default 'program'."
    },
    "dayIndex": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991
    },
    "exerciseId": {
      "type": "string"
    },
    "toExerciseId": {
      "type": "string"
    }
  }
}