_ registry / mcp streamable-http · checked 48m ago

calculatorforgrading

https://calculatorforgrading.com

Registry code: c8ef9cf1b55b7aae

api record

Grade, GPA and test-score arithmetic from calculatorforgrading.com. Use the tools for every number: percent and letter from questions wrong, score needed on a final, weighted average, GPA, SAT/ACT/MCAT practice-test scores, and grading-scale tables with sources. Never ask for names, student IDs or school names; only numbers and letters are needed. Letter cut-offs differ by school: say which scale was used and tell the user to check their syllabus. Results are estimates for practice and planning, not official grades or scores. Answer in the user's language, keep the one-line method, and keep…

endpoint
https://calculatorforgrading.com/mcp?src=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 calculatorforgrading live?
Yes — it answered the hub's last check (checked 48m ago). It answered 100% of checks over the last 30 days.
Is calculatorforgrading free to use?
Yes — the hub reached it with no key and no payment.
What tools does calculatorforgrading have?
6 tools: grade_calculator, weighted_grade, test_score_calculator, grading_scale_facts, final_grade_needed, gpa_calculator.
Is calculatorforgrading 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
344ms

last good check

priced tools
0

of 6 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 6 tools
6 never probed 0 of 6 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.

  • grade_calculator unknown 48m ago

    Use this when a student or teacher wants the percent and letter grade for a test from the number of questions wrong (or correct), e.g. "7 wrong out of 40". Returns the percent, the letter on the chosen scale, how many more correct answers reach the next letter, and optionally a chart of every possible number wrong. Do not use it for a final-exam target, weighted categories, GPA or test scores. Needs only numbers; never ask for names.

    mcp-tool

    {
  "type": "object",
  "required": [
    "total_questions"
  ],
  "properties": {
    "scale": {
      "enum": [
        "10_point",
        "7_point",
        "plus_minus",
        "pass_fail"
      ],
      "type": "string",
      "description": "10_point = A 90, B 80, C 70, D 60 (default); 7_point = A 93, B 85, C 77, D 70; plus_minus = the site's preset with A+ 97 ... D- 60; pass_fail = pass at 60."
    },
    "wrong": {
      "type": "integer",
      "minimum": 0,
      "description": "Questions wrong. Give wrong or correct, not both."
    },
    "correct": {
      "type": "integer",
      "minimum": 0,
      "description": "Questions correct. Give wrong or correct, not both."
    },
    "decimals": {
      "enum": [
        0,
        1,
        2
      ],
      "type": "integer",
      "description": "Decimals shown in the percent (default 0)."
    },
    "rounding": {
      "enum": [
        "nearest",
        "down"
      ],
      "type": "string",
      "description": "nearest rounds half up (default); down never rounds up, for teachers who truncate."
    },
    "include_chart": {
      "type": "boolean",
      "description": "Also return a chart row for each possible number wrong (first 60 rows)."
    },
    "custom_cutoffs": {
      "type": "array",
      "items": {
        "type": "number"
      },
      "description": "Optional own cut-off percents, highest grade first, strictly descending (10_point: A, B, C, D = 4 numbers; plus_minus: 12 numbers). Use only when the user gives them."
    },
    "total_questions": {
      "type": "integer",
      "maximum": 10000,
      "minimum": 1,
      "description": "Number of questions or points on the test."
    }
  },
  "additionalProperties": false
}
    arguments 63 lines
  • weighted_grade unknown never probed

    Use this when a student wants the weighted course grade from categories such as homework 20%, tests 50%, final 30%. Each row has a score (percent, a fraction like 45/50, or a letter) and a weight; rows without a score count as still open. Returns the weighted average, the letter, how much weight is graded and open, and optionally what the open part must average to reach a target grade. Do not use it for a single final-exam question without categories.

    mcp-tool

    {
  "type": "object",
  "required": [
    "rows"
  ],
  "properties": {
    "rows": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "weight"
        ],
        "properties": {
          "name": {
            "type": "string",
            "maxLength": 40,
            "description": "Optional category label such as Homework. Never a person's name."
          },
          "score": {
            "type": [
              "number",
              "string"
            ],
            "description": "Percent (92), fraction (45/50) or letter (B+). Leave out for a category not graded yet."
          },
          "weight": {
            "type": "number",
            "maximum": 1000,
            "minimum": 0,
            "description": "Weight of the category (usually percent of the course)."
          }
        },
        "additionalProperties": false
      },
      "maxItems": 30,
      "minItems": 1
    },
    "scale": {
      "enum": [
        "10_point",
        "plus_minus"
      ],
      "type": "string",
      "description": "10_point (default) or plus_minus."
    },
    "target_grade": {
      "type": [
        "string",
        "number"
      ],
      "description": "Optional wanted course grade (percent or letter)."
    }
  },
  "additionalProperties": false
}
    arguments 56 lines
  • test_score_calculator unknown never probed

    Use this when a student wants a score from a published practice test: SAT (College Board digital practice tests 4-11, correct answers per section to score ranges), ACT (practice tests 1-4 and the National test, correct answers per section to scale scores and Composite) or MCAT (four section scores 118-132 to total and AAMC percentile). Returns the score with the source table and fetch date. Not for official score reports, other tests, or predicting a real exam.

    mcp-tool

    {
  "type": "object",
  "required": [
    "test"
  ],
  "properties": {
    "test": {
      "enum": [
        "sat",
        "act",
        "mcat"
      ],
      "type": "string"
    },
    "mcat_cars": {
      "type": "integer",
      "maximum": 132,
      "minimum": 118
    },
    "practice_test": {
      "type": [
        "integer",
        "string"
      ],
      "description": "SAT: practice test number 4-11. ACT: 1, 2, 3, 4 or national."
    },
    "mcat_chem_phys": {
      "type": "integer",
      "maximum": 132,
      "minimum": 118
    },
    "mcat_psych_soc": {
      "type": "integer",
      "maximum": 132,
      "minimum": 118
    },
    "act_math_correct": {
      "type": "integer",
      "maximum": 41,
      "minimum": 0
    },
    "mcat_bio_biochem": {
      "type": "integer",
      "maximum": 132,
      "minimum": 118
    },
    "sat_math_correct": {
      "type": "integer",
      "maximum": 54,
      "minimum": 0,
      "description": "SAT: correct answers in Math (both modules)."
    },
    "act_english_correct": {
      "type": "integer",
      "maximum": 40,
      "minimum": 0
    },
    "act_reading_correct": {
      "type": "integer",
      "maximum": 27,
      "minimum": 0
    },
    "act_science_correct": {
      "type": "integer",
      "maximum": 34,
      "minimum": 0
    },
    "sat_reading_writing_correct": {
      "type": "integer",
      "maximum": 66,
      "minimum": 0,
      "description": "SAT: correct answers in Reading and Writing (both modules)."
    }
  },
  "additionalProperties": false
}
    arguments 76 lines
  • grading_scale_facts unknown never probed

    Use this when someone asks what a grading scale is: the 10-point scale (A 90-100), the 7-point scale (A 93-100), the plus-minus scale with GPA points on 4.0 and 4.3, or the College Board percent-to-GPA table. Returns the cut-offs, the named sources and the date they were checked. Use it instead of answering from memory; there is no national scale and schools differ.

    mcp-tool

    {
  "type": "object",
  "required": [
    "scale"
  ],
  "properties": {
    "scale": {
      "enum": [
        "10_point",
        "7_point",
        "plus_minus",
        "college_board"
      ],
      "type": "string"
    }
  },
  "additionalProperties": false
}
    arguments 18 lines
  • final_grade_needed unknown 48m ago

    Use this when a student asks what score they need on a final exam (or last assignment) to reach a target grade, given the current grade and how much the final counts. Returns the needed percent, whether it is secured or out of reach, what a 0 and a 100 would leave, and the need for every letter. Works with percents (current_grade_percent + final_weight_percent) or with points (points_earned_so_far, points_possible_so_far, final_exam_points). Do not use it for a weighted average of categories.

    mcp-tool

    {
  "type": "object",
  "required": [
    "target_grade"
  ],
  "properties": {
    "scale": {
      "enum": [
        "10_point",
        "plus_minus"
      ],
      "type": "string",
      "description": "10_point (default) or plus_minus, used to read a letter target."
    },
    "target_grade": {
      "type": [
        "string",
        "number"
      ],
      "description": "Wanted grade: a percent (90) or a letter (B+)."
    },
    "final_exam_points": {
      "type": "number",
      "description": "Points mode: points the final is worth."
    },
    "final_weight_percent": {
      "type": "number",
      "maximum": 100,
      "minimum": 0.01,
      "description": "How much of the course grade the final counts, in percent."
    },
    "points_earned_so_far": {
      "type": "number",
      "description": "Points mode: points earned so far."
    },
    "current_grade_percent": {
      "type": "number",
      "maximum": 150,
      "minimum": 0,
      "description": "Current course grade in percent before the final."
    },
    "points_possible_so_far": {
      "type": "number",
      "description": "Points mode: points possible so far."
    }
  },
  "additionalProperties": false
}
    arguments 48 lines
  • gpa_calculator unknown 48m ago

    Use this when a student wants their GPA from letter grades and credits, high school (honors +0.5, AP/IB +1.0 on passing grades, weighted and unweighted) or college (credit hours, unweighted). Returns unweighted and weighted GPA with the points of each course. Credits default to 1 (hs) or 3 (college). Do not use it for a single test grade or for a school-specific formula such as UC or LSAC.

    mcp-tool

    {
  "type": "object",
  "required": [
    "courses"
  ],
  "properties": {
    "mode": {
      "enum": [
        "hs",
        "college"
      ],
      "type": "string",
      "description": "hs = high school with weighting (default); college = unweighted."
    },
    "scale": {
      "enum": [
        "4.0",
        "4.3"
      ],
      "type": "string",
      "description": "4.0 (A+ counts 4.0, default) or 4.3 (A+ counts 4.3)."
    },
    "courses": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "letter"
        ],
        "properties": {
          "level": {
            "enum": [
              "regular",
              "honors",
              "ap"
            ],
            "type": "string",
            "description": "regular (default), honors or ap (AP/IB)."
          },
          "letter": {
            "enum": [
              "A+",
              "A",
              "A-",
              "B+",
              "B",
              "B-",
              "C+",
              "C",
              "C-",
              "D+",
              "D",
              "D-",
              "F"
            ],
            "type": "string",
            "description": "Letter grade."
          },
          "credits": {
            "type": "number",
            "maximum": 30,
            "description": "Credits or credit hours.",
            "exclusiveMinimum": 0
          }
        },
        "additionalProperties": false
      },
      "maxItems": 40,
      "minItems": 1
    }
  },
  "additionalProperties": false
}
    arguments 73 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 c8ef9cf1b55b7aae.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/c8ef9cf1b55b7aae/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/c8ef9cf1b55b7aae/badge.svg)](https://brick.blue/agent/c8ef9cf1b55b7aae?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.