# io.github.farssaadeldin7-ux/professor-mind-reader (mcpb · professor-mind-reader.mcpb)

Reverse-engineer a marking rubric into the handful of criteria that actually move the mark, then...

- Trust score: 35/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-22

## Components

- mcpb · `professor-mind-reader.mcpb`: 35/100 (this document), [markdown](https://verifymcp.io/servers/farssaadeldin7-ux-professor-mind-reader/professor-mind-reader.md), [page](https://verifymcp.io/servers/farssaadeldin7-ux-professor-mind-reader/professor-mind-reader)

## Channel facts

- Registry: `mcpb`
- Package: `https://github.com/farssaadeldin7-ux/claude-plugin-suite/releases/download/mcpb-v0.1.3/professor-mind-reader.mcpb`
- Version: `0.1.3`
- Transport: `stdio`
- SHA-256: `d0190252fb4ebfd48235b8accbba38ce7036c1d9bcd13890b1a9046fe4b24b41`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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 2026-10-22.

- **Supply Chain Security**: 0/100
  - No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
  - Known CVEs could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).
  - Install-script risk not yet assessed.
  - Dependency health could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).
- **Provenance & Transparency**: 26/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: no license is declared.
  - Maintenance history not yet determined.
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 84/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1285 tokens (~98/item across 13 items; 13 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 95/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 84% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 13 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

**Unverified: 2 categories.** Categories scored 0 because we could not verify them: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the io.github.farssaadeldin7-ux/professor-mind-reader MCP server?

io.github.farssaadeldin7-ux/professor-mind-reader ships as an MCPB bundle, a single file you download and open in an MCP host that supports MCPB bundles, such as Claude Desktop. The host reads the launch command from the bundle's own manifest, so there is no command to copy. Before opening it, check the file's SHA-256 matches the one the MCP registry declares for it, d0190252fb4ebfd48235b8accbba38ce7036c1d9bcd13890b1a9046fe4b24b41; the commands to do that are on this page. If it does not match, do not open it.

- Download bundle: `https://github.com/farssaadeldin7-ux/claude-plugin-suite/releases/download/mcpb-v0.1.3/professor-mind-reader.mcpb`
- SHA-256: `d0190252fb4ebfd48235b8accbba38ce7036c1d9bcd13890b1a9046fe4b24b41`

### Verify on macOS / Linux

```bash
echo "d0190252fb4ebfd48235b8accbba38ce7036c1d9bcd13890b1a9046fe4b24b41  professor-mind-reader.mcpb" | shasum -a 256 -c
```

### Verify on Windows (PowerShell)

```powershell
(Get-FileHash -Algorithm SHA256 .\professor-mind-reader.mcpb).Hash -eq "d0190252fb4ebfd48235b8accbba38ce7036c1d9bcd13890b1a9046fe4b24b41"
```

## 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.

### 2026-10-22 (score 35, −1)

- [functional regression] Maintenance: pass → unverified

### 2026-10-21 (score 36)

First indexed and scored.

## MCP tools (13)

### `verb_ladder` (~117 tokens)

The seven-rung verb ladder that fixes the cognitive level a rubric criterion demands: the verbs on each rung, what the marker must be able to underline, the one-level-down failure, the demotion signals and the promotion moves. Pass a verb for an exact table lookup of its rung — an unrecognised verb is reported as such, never guessed at. It does not judge whether a draft reaches a rung.

Input parameters:

- `verb` (string): A rubric verb to look up, e.g. "critique" or "account for".

### `band_descriptors` (~110 tokens)

The band tables: naming mapped across UK, US and ECTS systems, what actually separates each band, the 2:1 to 1st pivot, the descriptor-phrase translations and the honesty rules for positioning. Pass a phrase to translate wording from a published descriptor. Reference data only — it does not position a draft, and nothing in it yields a percentage.

Input parameters:

- `phrase` (string): A phrase from a published descriptor, e.g. "sophisticated" or "some evidence of".

### `hidden_rubric` (~136 tokens)

The standing checklist of conventions markers reward that printed rubrics usually omit — each with its test, why it is rewarded and its failure signature — plus the rules for reporting them. All of it is inferred convention, not guarantee, and the data says so. Running the tests against a draft is the skill's job. Pass an item id to fetch one item.

Input parameters:

- `item` (string): Optional single item: question_asked, signposting, set_reading, counter_argument, citation_style, first_last_paragraphs, stable_definitions, word_count, calibrated_hedging, source_recency_range, pres…

### `effort_map` (~142 tokens)

Compute the word budget from the rubric weights: target words and marks per 100 words per criterion, and — where actual section word counts are supplied — the investment ratio with its verdict from the threshold table (over-invested above 1.5, under-invested below 0.5). Arithmetic only; whether a heavy section is justified by a high-verb criterion is the audit's call. Requires a paid plan.

Input parameters:

- `criteria` (array, required): One entry per criterion: {name, weight (percent, e.g. 40), actual_words (optional)}.
- `total_words` (number, required): The assignment word count, e.g. 2500.

### `audit_scorecard` (~131 tokens)

Turn the audit's per-criterion verdicts into marks at stake (weight times the gap: unmet 1.0, partially met 0.5, met 0) and a ranked fix list — standing-rule overrides first, then marks at stake divided by effort, capped at five items. The verdicts are the audit's judgement, supplied as input with a verbatim quote behind each; this tool only counts and orders them. Requires a paid plan.

Input parameters:

- `criteria` (array, required): One entry per criterion: {name, weight (percent), verdict, fix (optional), effort (optional)}.

### `log_audit` (~167 tokens)

Record an audit's band-range call and top fix in the local audit log so the actual result can be checked against it later. A positioning that is never checked has no error bar. Requires a paid plan; the licence check is the only thing this tool sends anywhere.

Input parameters:

- `assignment` (string): A short label for later recognition, e.g. "Org behaviour essay, Q2".
- `band_ceiling` (string): Upper end of the range, same ids.
- `band_floor` (string): Lower end of the range: fail, third, two_two, two_one, first.
- `notes` (string)
- `top_fix` (string): The first item on the ranked fix list.
- `total_marks_at_stake` (number): From audit_scorecard.

### `record_result` (~77 tokens)

Record the band the marked work actually came back in, against a logged audit. This is what gives the positioning record an error bar. Requires a paid plan.

Input parameters:

- `actual_band` (string, required): One of: fail, third, two_two, two_one, first.
- `audit_id` (string, required)
- `notes` (string)

### `review_audits` (~62 tokens)

The record of past audits and a plain tally of how the band-range calls landed — within the range, one band outside, further out. Counting only; it makes no new claim. Requires a paid plan.

Input parameters:

- `limit` (number): Default 20.

### `license_status` (~51 tokens)

Check the Professor Mind-Reader licence on this machine: plan, included capabilities, remaining quota and seat usage. Call this when a paid tool reports a licence problem, or when the user asks what their plan includes.

### `license_activate` (~68 tokens)

Store and activate a Professor Mind-Reader licence key on this machine. Use when the user pastes a licence key, or after a purchase completes.

Input parameters:

- `license_key` (string, required): The licence key, e.g. PS-XXX-00000-00000-00000-0000

### `start_checkout` (~75 tokens)

Begin a Professor Mind-Reader purchase. Returns a Stripe Checkout link. Call list_plans first if the user has not chosen a plan.

Input parameters:

- `email` (string): Email address for the receipt and licence.
- `plan` (string, required): Plan id: "pro" or "team". Use list_plans to see the options.

### `list_plans` (~25 tokens)

List the available Professor Mind-Reader plans, prices and what each one includes.

### `billing_portal` (~31 tokens)

Open the Stripe billing portal to change plan, update the card, or cancel the Professor Mind-Reader subscription.

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/farssaadeldin7-ux-professor-mind-reader/professor-mind-reader#diagnostics

## Score history

- 2026-10-22: 35
- 2026-10-21: 36

## Common questions

### What is the io.github.farssaadeldin7-ux/professor-mind-reader MCP server?

io.github.farssaadeldin7-ux/professor-mind-reader is an MCP server listed in the public MCP registry as io.github.farssaadeldin7-ux/professor-mind-reader. Reverse-engineer a marking rubric into the handful of criteria that actually move the mark, then... This page covers its MCPB bundle (https://github.com/farssaadeldin7-ux/claude-plugin-suite/releases/download/mcpb-v0.1.3/professor-mind-reader.mcpb).

### Is the io.github.farssaadeldin7-ux/professor-mind-reader MCP server safe to use?

io.github.farssaadeldin7-ux/professor-mind-reader scores 35 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 io.github.farssaadeldin7-ux/professor-mind-reader MCP server expose?

io.github.farssaadeldin7-ux/professor-mind-reader exposes 13 tools: verb_ladder, band_descriptors, hidden_rubric, effort_map, audit_scorecard, and 8 more. Their descriptions and schemas cost roughly 1,192 tokens of context every time the server is loaded.

## Links

- Repository: https://github.com/farssaadeldin7-ux/claude-plugin-suite
- Changelog RSS feed: https://verifymcp.io/servers/farssaadeldin7-ux-professor-mind-reader/professor-mind-reader.xml
- Changelog JSON feed: https://verifymcp.io/servers/farssaadeldin7-ux-professor-mind-reader/professor-mind-reader.json
- HTML version of this page: https://verifymcp.io/servers/farssaadeldin7-ux-professor-mind-reader/professor-mind-reader