# ScoreFluent (remote · api.scorefluent.com)

English exam prep: exam facts, practice questions and writing scores for PTE, IELTS, TOEFL.

- Trust score: 75/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `api.scorefluent.com`: 75/100 (this document), [markdown](https://verifymcp.io/servers/com-scorefluent-scorefluent/mcp-copilot.md), [page](https://verifymcp.io/servers/com-scorefluent-scorefluent/mcp-copilot)

## Channel facts

- Endpoint: `https://api.scorefluent.com/mcp/copilot`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.0`

## 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 2026-11-21.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - 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**: 44/100
  - 0% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1333 tokens (~121/item across 11 items; 10 tools + 1 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 53/100
  - Stability observed for 16 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 91/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 70% 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 10 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).
  - Supports UI / widget rendering.

## Install

### How do I install the ScoreFluent MCP server?

ScoreFluent is a hosted endpoint at https://api.scorefluent.com/mcp/copilot, 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-scorefluent-scorefluent 'https://api.scorefluent.com/mcp/copilot'
```

### Cursor

```json
{
  "mcpServers": {
    "com-scorefluent-scorefluent": {
      "url": "https://api.scorefluent.com/mcp/copilot"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-scorefluent-scorefluent": {
      "type": "http",
      "url": "https://api.scorefluent.com/mcp/copilot"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-scorefluent-scorefluent]
url = "https://api.scorefluent.com/mcp/copilot"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-scorefluent-scorefluent": {
      "type": "remote",
      "url": "https://api.scorefluent.com/mcp/copilot",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-scorefluent-scorefluent --url 'https://api.scorefluent.com/mcp/copilot' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-scorefluent-scorefluent:
    url: "https://api.scorefluent.com/mcp/copilot"
```

### Netclaw

```json
{
  "McpServers": {
    "com-scorefluent-scorefluent": {
      "Transport": "http",
      "Url": "https://api.scorefluent.com/mcp/copilot"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-scorefluent-scorefluent -t streamable-http -u 'https://api.scorefluent.com/mcp/copilot'
```

### Other

```json
{
  "mcpServers": {
    "com-scorefluent-scorefluent": {
      "type": "http",
      "url": "https://api.scorefluent.com/mcp/copilot"
    }
  }
}
```

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.

### 2026-11-21 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-20 (score 74, 0)

- [security] Tool “start_diagnostic” rewrote its description, which is the text the model reads
- [cosmetic] Tool “start_diagnostic” changed its title: Start a diagnostic → Start Exam Match

### 2026-11-19 (score 74, +1)

- [security] Tool “start_diagnostic” rewrote its description, which is the text the model reads

### 2026-11-17 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-16 (score 72, 0)

- [functional regression] Schema quality: 1118 → 1334
- [functional] New tool “question_type_skills”

### 2026-11-15 (score 72, 0)

- [security] Tool “score_writing” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: pass → fail

### 2026-11-14 (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.

### 2026-11-12 (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.

## MCP tools (10)

### `exam_overview` (~156 tokens)

Exam overview

Use this when a student asks what an English exam contains, how a task type is scored, how long a section is, what the score scale is, or where to start preparing. Returns the exam sections with task types, question counts and time limits, the writing and speaking scoring criteria (writing with word limits), and links to ScoreFluent guides. Do not use this to score or mark a student's answer; it only describes the exam.

Input parameters:

- `exam` (string, required): Exam id, e.g. "pte", "toefl", "ielts", "languagecert_academic".
- `taskType` (string): Optional task-type slug (e.g. "write-essay") to narrow the answer to one task.

Output parameters:

- `exam` (string)
- `label` (string)
- `links` (object)
- `markingNote` (string)
- `notes` (array)
- `scale` (object)
- `scoredBy` (string)
- `sections` (array)
- `speakingCriteria` (array)
- `writingRubrics` (array)

### `question_type_skills` (~216 tokens)

Question type skills

Use this when a student asks what a question type tests, which skills it needs, how to practise for it, or what mistakes people make on it (for example "what does IELTS Writing Task 2 test?" or "what skills does PTE Read Aloud need?"). Give the exam and, if you know it, the question type by name or slug; without a question type it lists the exam's question types so you can pick one. Returns the skills the question type tests, the kinds of practice ScoreFluent offers, common mistakes where we have them, and a link to the ScoreFluent skill map. Do not use this to score or mark a student's answer.

Input parameters:

- `exam` (string, required): Exam id, e.g. "pte", "toefl", "ielts", "languagecert_academic".
- `questionType` (string): Optional question type, by name ("Writing Task 2", "Read Aloud") or slug. Leave it out to list the exam's question types.

Output parameters:

- `commonMistakes` (array)
- `exam` (string)
- `examLabel` (string)
- `links` (object)
- `practice` (array)
- `questionType` (object)
- `questionTypes` (array)
- `skills` (array)

### `practice_question` (~192 tokens)

Practice question

Use this when a student wants a real practice question for an English exam task, for example "give me a PTE Write Essay prompt" or "a TOEFL listening question". Returns one random published question (prompt, passage, options, word limit, and an audio link for listening tasks) and a link where the student can answer it with the real timer and scoring. It never returns answers or model responses. Do not use it to check an answer; it only serves questions. For PTE Read Aloud or Describe Image, use speak_practice instead: it serves the question with a recorder so the student can answer and be scored in the chat.

Input parameters:

- `exam` (string): Exam id. Defaults to "pte".
- `taskType` (string, required): Task-type slug, e.g. "write-essay" or "listening-mcq-single". Call exam_overview to list the valid slugs.

Output parameters:

- `answerUrl` (string)
- `audioUrl` (string)
- `difficulty` (number)
- `estimatedDurationSeconds` (number|null)
- `exam` (string)
- `pillar` (string)
- `question` (object)
- `questionId` (string)
- `taskLabel` (string)
- `taskType` (string)

### `score_writing` (~312 tokens)

Score writing

Use this when a student pastes an essay, email or summary for a PTE Academic, LanguageCert Academic, TOEFL iBT, MET, CELPIP, IELTS Academic, IELTS General Training, Cambridge C1 Advanced, PTE Core or Oxford Test of English (beta) writing task and wants a score. Returns marks out of the exam task maximum, a score and one line of feedback for each marking criterion, and the top improvements. Pass the questionId from practice_question when the text answers one of our questions; otherwise pass the prompt the student wrote to. Pass exactly one of the two. Free up to a daily limit. This is the quick score: Personalised Tips on the site add sentence-level annotations and verified marks. When the student is signed in to ScoreFluent and the text answers one of our questions, the scored attempt is saved to their History.

Input parameters:

- `exam` (string, required): Exam id, e.g. "pte" or "toefl".
- `prompt` (string): The prompt the student wrote to, when the text does not answer one of our questions.
- `questionId` (string): The questionId returned by practice_question, when the text answers one of our questions.
- `taskType` (string, required): Writing task-type slug, e.g. "write-essay" or "summarize-written-text". Call exam_overview to list the valid slugs.
- `text` (string, required): The student's essay or summary, exactly as they wrote it.

Output parameters:

- `criteria` (array)
- `exam` (string)
- `fullReportUrl` (string)
- `improvements` (array)
- `marks` (object)
- `overallFeedback` (string)
- `questionId` (string)
- `taskType` (string)
- `tier` (string)
- `wordCount` (number)

### `start_diagnostic` (~89 tokens)

Start Exam Match

Use when a student does not know which exam to take (Exam Match) or knows the exam and wants a starting baseline (placement). Returns a link to the test on the site; do not try to run the test in chat.

Input parameters:

- `exam` (string): Exam id when the student already knows it, e.g. "pte". Omit when they are not sure which exam to take.

Output parameters:

- `kind` (string)
- `minutes` (number)
- `url` (string)
- `what` (string)

### `check_read_aloud` (~128 tokens)

Check a Read Aloud transcript

Use when a student has read a Read Aloud passage aloud and you have the transcript of what they said (for example from voice mode) but no audio. Compares the words said against the passage: omitted, inserted and substituted words and a word-accuracy percentage. CONTENT ONLY — pronunciation, fluency and prosody need a recording: offer speak_practice or the answer link for those.

Input parameters:

- `questionId` (string, required): The questionId returned by speak_practice or practice_question for a Read Aloud passage.
- `transcript` (string, required): What the student said, as text.

Output parameters:

- `accuracy` (number)
- `answerUrl` (string)
- `inserted` (array)
- `matched` (number)
- `omitted` (array)
- `passageWordCount` (number)
- `questionId` (string)
- `saidWordCount` (number)
- `scope` (string)
- `substituted` (array)

### `speak_practice` (~103 tokens)

Speaking practice

Use whenever a student asks for a PTE Read Aloud or Describe Image to practise, even without mentioning recording or scores. Lets them practise the speaking task and get pronunciation and fluency scores. Shows a recorder card; desktop web only today. Do not use for scoring text.

Input parameters:

- `exam` (string): Exam id. Defaults to "pte".
- `taskType` (string): "read-aloud" or "describe-image". Defaults to "read-aloud".

Output parameters:

- `answerUrl` (string)
- `exam` (string)
- `prompt` (object)
- `questionId` (string)
- `taskLabel` (string)
- `taskType` (string)
- `timeLimitSeconds` (number)

### `recorder_start` (~50 tokens)

Start a recording

Reserve a recording slot and get an upload URL. Called by the speaking recorder card only.

Input parameters:

- `deviceToken` (string, required)
- `mimeType` (string, required)
- `questionId` (string, required)

Output parameters:

- `attemptId` (string)
- `expiresInSeconds` (number)
- `uploadUrl` (string)

### `recorder_confirm` (~41 tokens)

Submit a recording

Confirm the upload and queue it for scoring. Called by the speaking recorder card only.

Input parameters:

- `attemptId` (string, required)
- `deviceToken` (string, required)

Output parameters:

- `ok` (boolean)

### `recorder_result` (~42 tokens)

Recording result

Read the scoring status and scores for a recording. Called by the speaking recorder card only.

Input parameters:

- `attemptId` (string, required)
- `deviceToken` (string, required)

Output parameters:

- `fullReportUrl` (string)
- `scores` (object)
- `status` (string)
- `transcript` (string)

## Diagnostics

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

## Score history

- 2026-11-21: 75
- 2026-11-20: 74
- 2026-11-19: 74
- 2026-11-18: 73
- 2026-11-17: 73
- 2026-11-16: 72
- 2026-11-15: 72
- 2026-11-14: 72
- 2026-11-13: 71
- 2026-11-12: 71
- 2026-11-11: 70
- 2026-11-10: 70
- 2026-11-09: 69
- 2026-11-08: 69
- 2026-11-07: 68
- 2026-11-06: 68
- 2026-11-05: 67

## Common questions

### What is the ScoreFluent MCP server?

ScoreFluent is an MCP server listed in the public MCP registry as com.scorefluent/scorefluent. English exam prep: exam facts, practice questions and writing scores for PTE, IELTS, TOEFL. This page covers its hosted endpoint (https://api.scorefluent.com/mcp/copilot).

### Is the ScoreFluent MCP server safe to use?

ScoreFluent scores 75 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 ScoreFluent MCP server expose?

ScoreFluent exposes 10 tools: exam_overview, question_type_skills, practice_question, score_writing, start_diagnostic, and 5 more. Their descriptions and schemas cost roughly 1,329 tokens of context every time the server is loaded.

### Does the ScoreFluent MCP server require authentication?

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

### Is the ScoreFluent MCP server still maintained?

ScoreFluent is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the ScoreFluent MCP server?

VerifyMCP ran 14 checks on ScoreFluent, covering TLS certificate, Authorization, HTTPS, HSTS header and 10 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://api.scorefluent.com/mcp/copilot
- Website: https://scorefluent.com/mcp
- Changelog RSS feed: https://verifymcp.io/servers/com-scorefluent-scorefluent/mcp-copilot.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-scorefluent-scorefluent/mcp-copilot/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-scorefluent-scorefluent/mcp-copilot.json
- HTML version of this page: https://verifymcp.io/servers/com-scorefluent-scorefluent/mcp-copilot
