_ registry / mcp streamable-http · checked 1h ago

ironledger-calculators

https://www.ironledger.app

Registry code: e8aff5f7d08bbd77

api record

Deterministic strength-training calculators from IronLedger. All tools are read-only calculations with no account. Loads are in kg or lb (pass unit). Each result includes a plain-English summary and a url to the same result on ironledger.app, which you can share with the user.

endpoint
https://www.ironledger.app/mcp
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is ironledger-calculators live?
Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.
Is ironledger-calculators free to use?
Yes — the hub reached it with no key and no payment.
What tools does ironledger-calculators have?
7 tools: rpe_target_load, warmup_sets, check_program_file, one_rep_max, plate_loading, powerlifting_score, rpe_estimate_max.
Is ironledger-calculators safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
100%

90 days 100%· all time 100%

latency
259ms

last good check

priced tools
0

of 7 tools

_ answered our checks, 90 days 1 checks · signed record
  • unknown → live
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

inferred, not observed

Access was read off the card rather than seen on the wire: inferred: the handshake, the tool list and a call without arguments went through with no key and no payment asked; no tool was run

_ what it can do 7 tools
7 never probed 0 of 7 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • rpe_target_load unknown never probed

    Find the load for a set of a given number of reps at a target RPE, from a known or estimated one-rep max. Rounded to the nearest 0.5.

    mcp-tool

    {
  "type": "object",
  "required": [
    "oneRepMax",
    "reps",
    "rpe"
  ],
  "properties": {
    "rpe": {
      "type": "number",
      "maximum": 10,
      "minimum": 5,
      "description": "Rating of perceived exertion, 5 to 10, read as reps in reserve (RPE 8 = 2 reps left). Half points allowed."
    },
    "reps": {
      "type": "integer",
      "maximum": 20,
      "minimum": 1,
      "description": "Target reps, 1 to 20."
    },
    "unit": {
      "enum": [
        "kg",
        "lb"
      ],
      "type": "string",
      "default": "kg",
      "description": "Weight unit for every load in and out: kg or lb."
    },
    "formula": {
      "enum": [
        "epley",
        "brzycki"
      ],
      "type": "string",
      "default": "epley",
      "description": "One-rep max formula: epley (weight × (1 + reps ÷ 30), the one the IronLedger app uses) or brzycki (weight × 36 ÷ (37 − reps))."
    },
    "oneRepMax": {
      "type": "number",
      "maximum": 2000,
      "minimum": 1,
      "description": "Your one-rep max (tested or estimated)."
    }
  },
  "additionalProperties": false
}
    arguments 47 lines
  • warmup_sets unknown never probed

    Build a warm-up ramp to a working weight: plate-friendly jumps, reps falling from 10 to singles, with the plates for each set. The same ramp the IronLedger app suggests.

    mcp-tool

    {
  "type": "object",
  "required": [
    "workingWeight"
  ],
  "properties": {
    "bar": {
      "type": "number",
      "maximum": 100,
      "minimum": 0,
      "description": "Bar weight in the chosen unit. Defaults to 20 kg or 45 lb."
    },
    "sets": {
      "type": "integer",
      "default": 4,
      "maximum": 12,
      "minimum": 1,
      "description": "Number of warm-up sets, 1 to 12."
    },
    "unit": {
      "enum": [
        "kg",
        "lb"
      ],
      "type": "string",
      "default": "kg",
      "description": "Weight unit for every load in and out: kg or lb."
    },
    "workingWeight": {
      "type": "number",
      "maximum": 2000,
      "minimum": 1,
      "description": "The first working set’s weight."
    }
  },
  "additionalProperties": false
}
    arguments 37 lines
  • check_program_file unknown never probed

    Check a training program written as a CSV or TSV file exactly as the IronLedger app will import it, before anyone loads it on a phone. Returns the weeks, sessions and exercises it creates, every skipped row and warning with its row number, the exercise names the app will question ("Did you mean ...?"), and names that will become new custom exercises. Use it whenever you write a program for someone to import into IronLedger, and fix anything it reports first. The app names the program after the file, so pass the file name you will give it.

    mcp-tool

    {
  "type": "object",
  "required": [
    "file"
  ],
  "properties": {
    "file": {
      "type": "string",
      "maxLength": 200000,
      "description": "The whole program file as text. Canonical header: Week,Day,Exercise,Sets,Reps,Load,RPE,RIR,Rest,Notes, then one row per exercise, such as 1,Day 1,Squat,5,5,100 kg,8,,3:00,belt. Wrap a cell that contains a comma in double quotes; never use a double quote inside a cell."
    },
    "fileName": {
      "type": "string",
      "maxLength": 120,
      "description": "The file name it will be saved as, such as \"Texas Method.csv\". The app names the program after it; without one the program is called Imported Spreadsheet."
    }
  },
  "additionalProperties": false
}
    arguments 19 lines
  • one_rep_max unknown 1h ago

    Estimate a one-rep max (1RM) from a set of weight × reps, with a percentage table and the load each rep count should allow. Epley by default, Brzycki optional. Estimates above 10 reps are flagged as less reliable.

    mcp-tool

    {
  "type": "object",
  "required": [
    "weight",
    "reps"
  ],
  "properties": {
    "reps": {
      "type": "integer",
      "maximum": 30,
      "minimum": 1,
      "description": "Reps completed, 1 to 30."
    },
    "unit": {
      "enum": [
        "kg",
        "lb"
      ],
      "type": "string",
      "default": "kg",
      "description": "Weight unit for every load in and out: kg or lb."
    },
    "weight": {
      "type": "number",
      "maximum": 2000,
      "minimum": 0.5,
      "description": "Weight lifted for the set."
    },
    "formula": {
      "enum": [
        "epley",
        "brzycki"
      ],
      "type": "string",
      "default": "epley",
      "description": "One-rep max formula: epley (weight × (1 + reps ÷ 30), the one the IronLedger app uses) or brzycki (weight × 36 ÷ (37 − reps))."
    }
  },
  "additionalProperties": false
}
    arguments 40 lines
  • plate_loading unknown 1h ago

    Work out which plates to put on each side of a barbell to reach a target weight, using standard gym plates or the plates you list. Reports the exact load and anything your plates can’t make.

    mcp-tool

    {
  "type": "object",
  "required": [
    "target"
  ],
  "properties": {
    "bar": {
      "type": "number",
      "maximum": 100,
      "minimum": 0,
      "description": "Bar weight in the chosen unit. Defaults to 20 kg or 45 lb."
    },
    "unit": {
      "enum": [
        "kg",
        "lb"
      ],
      "type": "string",
      "default": "kg",
      "description": "Weight unit for every load in and out: kg or lb."
    },
    "plates": {
      "type": "string",
      "description": "Plates available, heaviest first or in any order: \"25,20,15,10,5,2.5,1.25\" for as many as needed, or \"25:4,20:2\" for pairs owned. Defaults to standard gym plates (kg: 25 to 1.25; lb: 45 to 2.5)."
    },
    "target": {
      "type": "number",
      "maximum": 2000,
      "minimum": 0,
      "description": "Total weight wanted on the bar, including the bar."
    },
    "collars": {
      "type": "boolean",
      "default": false,
      "description": "Count a collar on each side."
    },
    "collarWeight": {
      "type": "number",
      "maximum": 20,
      "minimum": 0,
      "description": "Weight of each collar. Defaults to 2.5 kg or 5 lb."
    }
  },
  "additionalProperties": false
}
    arguments 45 lines
  • powerlifting_score unknown 1h ago

    Score a powerlifting total (or a bench press) against bodyweight with DOTS, IPF GL points and the original Wilks, using the coefficients the OpenPowerlifting rankings use.

    mcp-tool

    {
  "type": "object",
  "required": [
    "total",
    "bodyweight",
    "sex"
  ],
  "properties": {
    "sex": {
      "enum": [
        "male",
        "female"
      ],
      "type": "string",
      "description": "The formulas have separate male and female coefficients."
    },
    "unit": {
      "enum": [
        "kg",
        "lb"
      ],
      "type": "string",
      "default": "kg",
      "description": "Weight unit for every load in and out: kg or lb."
    },
    "event": {
      "enum": [
        "sbd",
        "bench"
      ],
      "type": "string",
      "default": "sbd",
      "description": "For IPF GL: sbd (full powerlifting total) or bench (bench press only)."
    },
    "total": {
      "type": "number",
      "maximum": 2000,
      "minimum": 1,
      "description": "Total lifted (squat + bench + deadlift), or the bench press for event \"bench\"."
    },
    "equipment": {
      "enum": [
        "raw",
        "equipped"
      ],
      "type": "string",
      "default": "raw",
      "description": "For IPF GL: raw (classic) or equipped."
    },
    "bodyweight": {
      "type": "number",
      "maximum": 400,
      "minimum": 20,
      "description": "Bodyweight in the chosen unit."
    }
  },
  "additionalProperties": false
}
    arguments 58 lines
  • rpe_estimate_max unknown never probed

    Estimate a one-rep max from weight, reps and RPE, treating RPE as reps in reserve (RPE 8 = 2 reps left) and applying the one-rep max formula to reps + reps in reserve.

    mcp-tool

    {
  "type": "object",
  "required": [
    "weight",
    "reps",
    "rpe"
  ],
  "properties": {
    "rpe": {
      "type": "number",
      "maximum": 10,
      "minimum": 5,
      "description": "Rating of perceived exertion, 5 to 10, read as reps in reserve (RPE 8 = 2 reps left). Half points allowed."
    },
    "reps": {
      "type": "integer",
      "maximum": 20,
      "minimum": 1,
      "description": "Reps completed, 1 to 20."
    },
    "unit": {
      "enum": [
        "kg",
        "lb"
      ],
      "type": "string",
      "default": "kg",
      "description": "Weight unit for every load in and out: kg or lb."
    },
    "weight": {
      "type": "number",
      "maximum": 2000,
      "minimum": 0.5,
      "description": "Weight lifted for the set."
    },
    "formula": {
      "enum": [
        "epley",
        "brzycki"
      ],
      "type": "string",
      "default": "epley",
      "description": "One-rep max formula: epley (weight × (1 + reps ÷ 30), the one the IronLedger app uses) or brzycki (weight × 36 ÷ (37 − reps))."
    }
  },
  "additionalProperties": false
}
    arguments 47 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id e8aff5f7d08bbd77.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/e8aff5f7d08bbd77/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/e8aff5f7d08bbd77/badge.svg)](https://brick.blue/agent/e8aff5f7d08bbd77?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
100%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.

_ also on ironledger.app 1 entry

Served from the same domain, which is what was measured. Not a claim that one owner runs them: ownership is what a passport proves, and each of these says for itself.