# Calculator for Grading (remote · calculatorforgrading.com)

Grades from questions wrong, final exam score needed, weighted grades, GPA, SAT/ACT/MCAT scores.

- Trust score: 73/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `calculatorforgrading.com`: 73/100 (this document), [markdown](https://verifymcp.io/servers/com-calculatorforgrading-calculatorforgrading/calculatorforgrading.md), [page](https://verifymcp.io/servers/com-calculatorforgrading-calculatorforgrading/calculatorforgrading)

## Channel facts

- Endpoint: `https://calculatorforgrading.com/mcp?src=mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 59/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1446 tokens (~241/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 40/100
  - Stability observed for 12 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 90/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 65% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Calculator for Grading MCP server?

Calculator for Grading is a hosted endpoint at https://calculatorforgrading.com/mcp?src=mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-calculatorforgrading-calculatorforgrading 'https://calculatorforgrading.com/mcp?src=mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-calculatorforgrading-calculatorforgrading": {
      "url": "https://calculatorforgrading.com/mcp?src=mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-calculatorforgrading-calculatorforgrading": {
      "type": "http",
      "url": "https://calculatorforgrading.com/mcp?src=mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-calculatorforgrading-calculatorforgrading]
url = "https://calculatorforgrading.com/mcp?src=mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-calculatorforgrading-calculatorforgrading": {
      "type": "remote",
      "url": "https://calculatorforgrading.com/mcp?src=mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-calculatorforgrading-calculatorforgrading --url 'https://calculatorforgrading.com/mcp?src=mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-calculatorforgrading-calculatorforgrading:
    url: "https://calculatorforgrading.com/mcp?src=mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-calculatorforgrading-calculatorforgrading": {
      "Transport": "http",
      "Url": "https://calculatorforgrading.com/mcp?src=mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-calculatorforgrading-calculatorforgrading -t streamable-http -u 'https://calculatorforgrading.com/mcp?src=mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-calculatorforgrading-calculatorforgrading": {
      "type": "http",
      "url": "https://calculatorforgrading.com/mcp?src=mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-04 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-27 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-25 (score 68, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-24 (score 67)

First indexed and scored.

## MCP tools (6)

### `grade_calculator` (~343 tokens)

Grade from questions wrong

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.

Input parameters:

- `correct` (integer): Questions correct. Give wrong or correct, not both.
- `custom_cutoffs` (array): 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.
- `decimals` (integer): Decimals shown in the percent (default 0).
- `include_chart` (boolean): Also return a chart row for each possible number wrong (first 60 rows).
- `rounding` (string): nearest rounds half up (default); down never rounds up, for teachers who truncate.
- `scale` (string): 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.
- `total_questions` (integer, required): Number of questions or points on the test.
- `wrong` (integer): Questions wrong. Give wrong or correct, not both.

Output parameters:

- `chart` (array)
- `correct` (integer)
- `letter` (string)
- `link` (string): Page of calculatorforgrading.com with the same inputs filled in.
- `next_letter`
- `percent_exact` (number)
- `percent_shown` (number)
- `rule` (string)
- `scale` (string)
- `total_questions` (integer)
- `wrong` (integer)

### `final_grade_needed` (~257 tokens)

Score needed on the final

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.

Input parameters:

- `current_grade_percent` (number): Current course grade in percent before the final.
- `final_exam_points` (number): Points mode: points the final is worth.
- `final_weight_percent` (number): How much of the course grade the final counts, in percent.
- `points_earned_so_far` (number): Points mode: points earned so far.
- `points_possible_so_far` (number): Points mode: points possible so far.
- `scale` (string): 10_point (default) or plus_minus, used to read a letter target.
- `target_grade` (string|number, required): Wanted grade: a percent (90) or a letter (B+).

Output parameters:

- `final_counts_percent` (number)
- `hundred_on_final_gives_percent` (number)
- `hundred_on_final_letter` (string)
- `letters` (array)
- `link` (string): Page of calculatorforgrading.com with the same inputs filled in.
- `needed_on_final_percent` (number|null)
- `scale` (string)
- `target` (string)
- `target_percent` (number)
- `verdict` (string)
- `zero_on_final_gives_percent` (number)
- `zero_on_final_letter` (string)

### `weighted_grade` (~152 tokens)

Weighted average of categories

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.

Input parameters:

- `rows` (array, required)
- `scale` (string): 10_point (default) or plus_minus.
- `target_grade` (string|number): Optional wanted course grade (percent or letter).

Output parameters:

- `graded_weight_percent` (number)
- `letter` (string)
- `link` (string): Page of calculatorforgrading.com with the same inputs filled in.
- `needed_on_remaining_percent` (number|null)
- `note` (string)
- `open_weight_percent` (number)
- `scale` (string)
- `target_percent` (number)
- `verdict` (string)
- `weighted_average_percent` (number)

### `gpa_calculator` (~170 tokens)

GPA from course grades

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.

Input parameters:

- `courses` (array, required)
- `mode` (string): hs = high school with weighting (default); college = unweighted.
- `scale` (string): 4.0 (A+ counts 4.0, default) or 4.3 (A+ counts 4.3).

Output parameters:

- `courses` (array)
- `credits` (number)
- `gpa_unweighted` (number)
- `gpa_weighted` (number|null)
- `link` (string): Page of calculatorforgrading.com with the same inputs filled in.
- `mode` (string)
- `scale` (string)

### `test_score_calculator` (~277 tokens)

SAT, ACT and MCAT practice scores

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.

Input parameters:

- `act_english_correct` (integer)
- `act_math_correct` (integer)
- `act_reading_correct` (integer)
- `act_science_correct` (integer)
- `mcat_bio_biochem` (integer)
- `mcat_cars` (integer)
- `mcat_chem_phys` (integer)
- `mcat_psych_soc` (integer)
- `practice_test` (integer|string): SAT: practice test number 4-11. ACT: 1, 2, 3, 4 or national.
- `sat_math_correct` (integer): SAT: correct answers in Math (both modules).
- `sat_reading_writing_correct` (integer): SAT: correct answers in Reading and Writing (both modules).
- `test` (string, required)

Output parameters:

- `caveat` (string)
- `composite` (number|null)
- `link` (string): Page of calculatorforgrading.com with the same inputs filled in.
- `percentile_valid` (string)
- `practice_test` (string)
- `sections` (object): Per-section result; keys depend on the test.
- `source` (object)
- `test` (string)
- `total` (number|null)
- `total_high` (integer)
- `total_low` (integer)
- `total_percentile` (string|null)

### `grading_scale_facts` (~112 tokens)

Grading scale cut-offs with sources

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.

Input parameters:

- `scale` (string, required)

Output parameters:

- `checked` (string)
- `link` (string): Page of calculatorforgrading.com with the same inputs filled in.
- `note` (string)
- `rows` (array)
- `scale` (string)
- `sources` (array)
- `title` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-calculatorforgrading-calculatorforgrading/calculatorforgrading#diagnostics

## Score history

- 2026-11-05: 73
- 2026-11-04: 73
- 2026-11-03: 72
- 2026-11-02: 72
- 2026-11-01: 71
- 2026-10-31: 71
- 2026-10-30: 70
- 2026-10-29: 70
- 2026-10-28: 69
- 2026-10-27: 69
- 2026-10-26: 68
- 2026-10-25: 68
- 2026-10-24: 67

## Common questions

### What is the Calculator for Grading MCP server?

Calculator for Grading is an MCP server listed in the public MCP registry as com.calculatorforgrading/calculatorforgrading. Grades from questions wrong, final exam score needed, weighted grades, GPA, SAT/ACT/MCAT scores. This page covers its hosted endpoint (https://calculatorforgrading.com/mcp?src=mcp).

### Is the Calculator for Grading MCP server safe to use?

Calculator for Grading scores 73 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Calculator for Grading MCP server expose?

Calculator for Grading exposes 6 tools: grade_calculator, final_grade_needed, weighted_grade, gpa_calculator, test_score_calculator, grading_scale_facts. Their descriptions and schemas cost roughly 1,311 tokens of context every time the server is loaded.

### Does the Calculator for Grading MCP server require authentication?

No. We connected to Calculator for Grading without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Calculator for Grading MCP server still maintained?

Calculator for Grading is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://calculatorforgrading.com/mcp?src=mcp
- Website: https://calculatorforgrading.com/ai-assistants/
- Changelog RSS feed: https://verifymcp.io/servers/com-calculatorforgrading-calculatorforgrading/calculatorforgrading.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-calculatorforgrading-calculatorforgrading/calculatorforgrading.json
- HTML version of this page: https://verifymcp.io/servers/com-calculatorforgrading-calculatorforgrading/calculatorforgrading