# Speakeroo speaking coach (remote · mcp.speakeroo.app)

AI speaking coach: feedback on speeches from text or audio, plus topics, pronunciation and rubrics.

- Trust score: 85/100 (high trust)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `mcp.speakeroo.app`: 85/100 (this document), [markdown](https://verifymcp.io/servers/app-speakeroo-speaking-coach/mcp.md), [page](https://verifymcp.io/servers/app-speakeroo-speaking-coach/mcp)

## Channel facts

- Endpoint: `https://mcp.speakeroo.app/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.1`

## 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**: 77/100
  - 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.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 69/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1020 tokens (~145/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 100/100
  - No destabilizing schema changes in the last 30 days.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% 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 7 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 8 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).

## Install

### How do I install the Speakeroo speaking coach MCP server?

Speakeroo speaking coach is a hosted endpoint at https://mcp.speakeroo.app/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 app-speakeroo-speaking-coach 'https://mcp.speakeroo.app/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "app-speakeroo-speaking-coach": {
      "url": "https://mcp.speakeroo.app/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "app-speakeroo-speaking-coach": {
      "type": "http",
      "url": "https://mcp.speakeroo.app/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.app-speakeroo-speaking-coach]
url = "https://mcp.speakeroo.app/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "app-speakeroo-speaking-coach": {
      "type": "remote",
      "url": "https://mcp.speakeroo.app/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add app-speakeroo-speaking-coach --url 'https://mcp.speakeroo.app/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  app-speakeroo-speaking-coach:
    url: "https://mcp.speakeroo.app/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "app-speakeroo-speaking-coach": {
      "Transport": "http",
      "Url": "https://mcp.speakeroo.app/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add app-speakeroo-speaking-coach -t streamable-http -u 'https://mcp.speakeroo.app/mcp'
```

### Other

```json
{
  "mcpServers": {
    "app-speakeroo-speaking-coach": {
      "type": "http",
      "url": "https://mcp.speakeroo.app/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.

### 2026-11-19 (score 85, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “get_speaking_rubric” rewrote its description, which is the text the model reads
- [security] Tool “get_speech_topics” rewrote its description, which is the text the model reads
- [security] Tool “how_to_pronounce” rewrote its description, which is the text the model reads
- [security] Tool “list_filler_words” rewrote its description, which is the text the model reads

### 2026-11-15 (score 85, 0)

- [security] Stability: 0.97 → pass

### 2026-11-14 (score 85, +1)

- [functional improvement] Tool coverage: 86% → 100%
- [cosmetic] “analyze_speech” reworded the description of “mimeType”
- [cosmetic] “analyze_speech” reworded the description of “topic”
- [cosmetic] “analyze_transcript” reworded the description of “topic”
- [cosmetic] “analyze_transcript” reworded the description of “transcript”
- [cosmetic] “get_speech_topics” reworded the description of “category”
- [cosmetic] “get_speech_topics” reworded the description of “count”
- [cosmetic] “how_to_pronounce” reworded the description of “word”
- [cosmetic] “refine_transcript” reworded the description of “topic”
- [cosmetic] “refine_transcript” reworded the description of “transcript”

### 2026-11-13 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-11 (score 83, +1)

- [security] Tool “analyze_speech” rewrote its description, which is the text the model reads
- [security] Tool “analyze_transcript” rewrote its description, which is the text the model reads
- [functional] Server version: 1.0.1 → 1.0.2

### 2026-11-08 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-06 (score 81, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-11-04 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (7)

### `analyze_transcript` (~204 tokens)

Analyze a speech transcript

Coach a speech from its text. Returns weak and filler words with firmer alternatives, rhetorical devices, delivery and rhetoric feedback, grammar/vocabulary/coherence scores (1-10) on the Speakeroo rubric, and word-level issues with the excerpt and a fix. Input: 30-1500 words. Text cannot show pace, pauses, pitch or pronunciation; use analyze_speech with a recording for those. Free, 5 text analyses a day per network, or per account when signed in, shared with refine_transcript.

Input parameters:

- `context` (string): What the speech is for, so the feedback is calibrated to it. Defaults to general.
- `topic` (string): The question or prompt being answered, e.g. an IELTS cue card or interview question. If omitted, the feedback is not tied to a specific prompt.
- `transcript` (string, required): What was said, as plain text: a speech transcript or a draft you plan to say out loud.

Output parameters:

- `callToAction` (object)
- `coaching`: Weak and filler words, rhetorical devices and delivery/rhetoric feedback
- `context` (string)
- `issues`: Word-level grammar, vocabulary and filler issues with the excerpt and a fix
- `language`: Grammar, vocabulary and coherence scores on the Speakeroo rubric
- `unavailable` (array): Parts that could not be produced this time; the rest of the result stands
- `wordCount` (number)

### `refine_transcript` (~177 tokens)

Restructure a speech

Rewrite a speech into a clear structure (PREP, STAR, problem-solution, rule of three and others) chosen to fit it. Returns the rewritten sections, the structure with a 1-10 score for how well the original already followed it, a summary of what changed and one delivery tip. Input: 30-1500 words. Shares the daily text allowance with analyze_transcript.

Input parameters:

- `context` (string): What the speech is for, so the feedback is calibrated to it. Defaults to general.
- `topic` (string): The question or prompt being answered, e.g. an IELTS cue card or interview question. If omitted, the feedback is not tied to a specific prompt.
- `transcript` (string, required): What was said, as plain text: a speech transcript or a draft you plan to say out loud.

Output parameters:

- `callToAction` (object)
- `refinedVersion` (object)
- `wordCount` (number)

### `analyze_speech` (~314 tokens)

Analyze a speech recording

Analyze a spoken recording: it is transcribed, then returns everything analyze_transcript does plus delivery metrics only audio can give: words per minute, pace, pauses per minute, filler rate, pitch (median and range) and vocal expression, and pacing, pronunciation and engagement scores. Limits: up to 120 seconds and 10 MB; mp3, m4a/mp4, wav, webm, ogg or flac; at least 30 spoken words. Pass audioUrl (public https) or audioBase64. Free: 1 analysis a day per network, or per account when signed in; a try that fails on our side does not count, up to 3 tries a day. Audio is deleted once the response is sent.

Input parameters:

- `audioBase64` (string): The recording as base64 (a data: URL prefix is fine). Use this or audioUrl.
- `audioUrl` (string): A public https link to the recording. Use this or audioBase64.
- `context` (string): What the speech is for, so the feedback is calibrated to it. Defaults to general.
- `mimeType` (string): The audio type when it cannot be sniffed from the bytes, e.g. audio/mpeg. If omitted, Speakeroo tries to detect it from the bytes or URL.
- `topic` (string): The question or prompt being answered, e.g. an IELTS cue card or interview question. If omitted, the feedback is not tied to a specific prompt.

Output parameters:

- `callToAction` (object)
- `coaching`: Weak and filler words, rhetorical devices and delivery/rhetoric feedback
- `context` (string)
- `delivery` (object)
- `issues`: Word-level grammar, vocabulary and filler issues with the excerpt and a fix
- `language`: Every rubric area including pacing, pronunciation and engagement, which need the audio
- `transcript` (string)
- `unavailable` (array): Parts that could not be produced this time; the rest of the result stands
- `wordCount` (number)

### `get_speech_topics` (~71 tokens)

Get speech topics

Random speech topics to practise with: impromptu, persuasive, informative, presentation, IELTS Speaking Part 1 questions or Part 2 cue cards.

Input parameters:

- `category` (string, required): The kind of speech topic to generate.
- `count` (integer): How many topics to return. Defaults to 10.

Output parameters:

- `category` (string)
- `link` (string): A page on speakeroo.app with the full list and practice
- `title` (string)
- `topics` (array)

### `how_to_pronounce` (~65 tokens)

How to pronounce a word

How to pronounce an English word Speakeroo has a guide for: IPA, a plain respelling, syllables with the stressed one, sound tips, a note on the usual mistake and two example sentences.

Input parameters:

- `word` (string, required): The English word to look up.

Output parameters:

- `found` (boolean)
- `ipa` (string)
- `link` (string): A page on speakeroo.app with the full list and practice
- `note` (string)
- `respelling` (string)
- `sentences` (array)
- `similarWords` (array)
- `stressedSyllable` (number): 1-based
- `syllables` (array)
- `tips` (array)
- `word` (string)

### `get_speaking_rubric` (~61 tokens)

Get a speaking rubric

A four-level speaking rubric teachers use for speaking homework: fluency, pronunciation, vocabulary range and task completion, with a descriptor for every level. analyze_transcript and analyze_speech score on Speakeroo's own 1-10 rubric.

Output parameters:

- `criteria` (array)
- `link` (string): A page on speakeroo.app with the full list and practice
- `name` (string)

### `list_filler_words` (~31 tokens)

List filler words

The common filler words in spoken English grouped by what they do, and the steps to stop using them.

Output parameters:

- `groups` (array)
- `howToStop` (array)
- `link` (string): A page on speakeroo.app with the full list and practice

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/app-speakeroo-speaking-coach/mcp#diagnostics

## Score history

- 2026-11-21: 85
- 2026-11-20: 85
- 2026-11-19: 85
- 2026-11-18: 85
- 2026-11-17: 85
- 2026-11-16: 85
- 2026-11-15: 85
- 2026-11-14: 85
- 2026-11-13: 84
- 2026-11-12: 83
- 2026-11-11: 83
- 2026-11-10: 82
- 2026-11-09: 82
- 2026-11-08: 82
- 2026-11-07: 81
- 2026-11-06: 81
- 2026-11-05: 80
- 2026-11-04: 80
- 2026-11-03: 79
- 2026-11-02: 79
- 2026-11-01: 78
- 2026-10-31: 78
- 2026-10-30: 77
- 2026-10-29: 77
- 2026-10-28: 76
- 2026-10-27: 76
- 2026-10-26: 75
- 2026-10-25: 75
- 2026-10-24: 75
- 2026-10-23: 74

## Common questions

### What is the Speakeroo speaking coach MCP server?

Speakeroo speaking coach is an MCP server listed in the public MCP registry as app.speakeroo/speaking-coach. AI speaking coach: feedback on speeches from text or audio, plus topics, pronunciation and rubrics. This page covers its hosted endpoint (https://mcp.speakeroo.app/mcp).

### Is the Speakeroo speaking coach MCP server safe to use?

Speakeroo speaking coach scores 85 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 Speakeroo speaking coach MCP server expose?

Speakeroo speaking coach exposes 7 tools: analyze_transcript, refine_transcript, analyze_speech, get_speech_topics, how_to_pronounce, and 2 more. Their descriptions and schemas cost roughly 923 tokens of context every time the server is loaded.

### Does the Speakeroo speaking coach MCP server require authentication?

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

### Is the Speakeroo speaking coach MCP server still maintained?

Speakeroo speaking coach 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 Speakeroo speaking coach MCP server?

VerifyMCP ran 13 checks on Speakeroo speaking coach, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 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://mcp.speakeroo.app/mcp
- Repository: https://github.com/chocopie8/speakeroo-mcp
- Website: https://speakeroo.app/mcp?utm_source=mcp-registry&utm_medium=listing
- Changelog RSS feed: https://verifymcp.io/servers/app-speakeroo-speaking-coach/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/app-speakeroo-speaking-coach/mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/app-speakeroo-speaking-coach/mcp.json
- HTML version of this page: https://verifymcp.io/servers/app-speakeroo-speaking-coach/mcp
