# PrePublish - YouTube script QA (remote · mcp.prepublish.ai)

Audit a YouTube script before recording: hook, pacing, drop-off risk, copy-paste rewrites.

- Trust score: 70/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- remote · `mcp.prepublish.ai`: 70/100 (this document), [markdown](https://verifymcp.io/servers/ai-prepublish-script-audit/mcp.md), [page](https://verifymcp.io/servers/ai-prepublish-script-audit/mcp)

## Channel facts

- Endpoint: `https://mcp.prepublish.ai`
- 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 2026-09-20.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 5 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - 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**: 69/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1332 tokens (~222/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**: 33/100
  - Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **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.
- **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 PrePublish - YouTube script QA MCP server?

PrePublish - YouTube script QA is a hosted endpoint at https://mcp.prepublish.ai/, 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 ai-prepublish-script-audit 'https://mcp.prepublish.ai/'
```

### Cursor

```json
{
  "mcpServers": {
    "ai-prepublish-script-audit": {
      "url": "https://mcp.prepublish.ai/"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-prepublish-script-audit": {
      "type": "http",
      "url": "https://mcp.prepublish.ai/"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ai-prepublish-script-audit]
url = "https://mcp.prepublish.ai/"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-prepublish-script-audit": {
      "type": "remote",
      "url": "https://mcp.prepublish.ai/",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-prepublish-script-audit --url 'https://mcp.prepublish.ai/' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-prepublish-script-audit:
    url: "https://mcp.prepublish.ai/"
```

### Netclaw

```json
{
  "McpServers": {
    "ai-prepublish-script-audit": {
      "Transport": "http",
      "Url": "https://mcp.prepublish.ai/"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-prepublish-script-audit -t streamable-http -u 'https://mcp.prepublish.ai/'
```

### Other

```json
{
  "mcpServers": {
    "ai-prepublish-script-audit": {
      "type": "http",
      "url": "https://mcp.prepublish.ai/"
    }
  }
}
```

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.

### 2026-09-20 (score 70, 0)

- [cosmetic] “audit_hook” reworded the description of “email”
- [cosmetic] “audit_script” reworded the description of “email”

### 2026-09-18 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-16 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-14 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-13 (score 67, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “audit_script” rewrote its description, which is the text the model reads
- [security] Tool “script_runtime” rewrote its description, which is the text the model reads
- [cosmetic] Tool “get_audit” changed its title: Collect a PrePublish audit by id → Collect a Prepublish audit by id

### 2026-09-12 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-11 (score 66, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-09-10 (score 66)

First indexed and scored.

## MCP tools (6)

### `audit_script` (~354 tokens)

Audit a YouTube script before recording

Run Prepublish's full audit on a YouTube script the user has already written. Returns hook, structure and pacing scores, a script-level attention-risk map naming the passages most likely to lose viewers, and a copy-paste rewrite for each flagged passage. Choose this when the user has a finished or near-finished draft and wants to know what is weak before they record. Do not use it to generate a script, to review a published video, or to check grammar. A free result is released by email, so ask the user for an address rather than guessing one. This is a text-only check of an unrecorded script. It maps relative attention risk inside the draft. It does not measure or predict published YouTube retention, and it cannot account for delivery, editing, thumbnail, topic or distribution.

Input parameters:

- `audience` (string): Target audience, only if the user said it.
- `category` (string): Video category, only if the user said it.
- `email` (string): Where the free result is sent. Required for every anonymous audit: the backend rejects the request without it. Ask the user; never invent it. When the caller is authenticated with a Prepublish API ke…
- `script_text` (string, required): The script text as the user wrote it. Paste it verbatim; do not rewrite, summarise or clean it first.
- `video_duration_seconds` (integer): Intended runtime in seconds, only if the user stated one. Used for pacing; never assumed.
- `video_title` (string, required): The title the user plans to publish under. The audit checks whether the script delivers this promise.

### `get_audit` (~127 tokens)

Collect a Prepublish audit by id

Fetch the current state of an audit that was started earlier, using the analysis_id that audit_script returned. Use this when a previous audit was still running, or when the user refers back to an audit from earlier in the conversation. It performs no new analysis and costs nothing. This is a text-only check of an unrecorded script. It maps relative attention risk inside the draft. It does not measure or predict published YouTube retention, and it cannot account for delivery, editing, thumbnail, topic or distribution.

Input parameters:

- `analysis_id` (string, required): The analysis_id returned by audit_script.

### `audit_hook` (~235 tokens)

Score the opening of a YouTube script

Score just the opening lines of a YouTube script: how much attention each sentence pulls, whether it opens a curiosity gap, how far away the payoff sits, plus the top issues and rewritten alternatives. Choose this when the user shares only a hook or opening paragraph, or wants a fast second opinion before auditing a whole draft. Cheaper and narrower than audit_script. This is a text-only check of an unrecorded script. It maps relative attention risk inside the draft. It does not measure or predict published YouTube retention, and it cannot account for delivery, editing, thumbnail, topic or distribution.

Input parameters:

- `email` (string): Only needed once the free anonymous hook check for the day is used. Ask the user; never invent it. When the caller is authenticated with a Prepublish API key the result comes back in the conversation…
- `hook_text` (string, required): The opening lines exactly as written, ideally the first 15 to 30 seconds of speech.
- `niche` (string): Channel niche, only if the user said it. Sharpens the comparison.

### `check_authenticity` (~150 tokens)

Check a script for reused or inauthentic content risk

Check a script against YouTube's inauthentic-content expectations: whether it reads as mass-produced, templated or repetitive, which signals fire, and what to change. Returns a score, a risk level, the firing signals with quotes, and remediation steps. Choose this when the user worries about reused content, AI-sounding scripts, or a channel that repeats a formula. This reports text-level signals only; it is not a monetisation decision and does not speak for YouTube.

Input parameters:

- `script_text` (string, required): The script text as the user wrote it. Paste it verbatim; do not rewrite, summarise or clean it first.
- `video_title` (string, required): The planned title.

### `policy_preflight` (~174 tokens)

Pre-flight a script against YouTube advertiser and monetisation policy

Check a script before recording for the YouTube policy categories it may touch: which category families are implicated, the consequence family for each, a verdict and flag counts. Each category cites YouTube's own published policy page. Choose this when the user is writing about sensitive subject matter and asks whether it is safe to monetise. The quoted passages and their suggested rewrites are part of the paid audit, so the free result may return counts with locked quotes. It reports risk against published policy text; it is not a monetisation guarantee and does not speak for YouTube.

Input parameters:

- `script` (string, required): The script text as written, at least 200 characters. Below that there is not enough context for a policy read.
- `title` (string): The planned title, if the user has one. Titles are checked too.

### `script_runtime` (~175 tokens)

Convert script length to spoken runtime

Convert a word count, or a pasted script, into a spoken runtime range, and convert a target runtime back into a word budget. Rates come from Prepublish's own measurement of 349 videos: 25th percentile 160 words per minute, median 181, 75th percentile 201. Choose this for "how long will this script run" or "how many words for a ten-minute video". It is arithmetic on speaking rate only: it excludes pauses, B-roll and demonstrations, so a finished edit usually runs longer.

Input parameters:

- `script_text` (string): A script to count. Provide this or word_count or target_minutes.
- `target_minutes` (number): A target runtime in minutes, to convert into a word budget.
- `word_count` (integer): A word count, if the user already knows it.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-prepublish-script-audit/mcp#diagnostics

## Score history

- 2026-09-20: 70
- 2026-09-19: 70
- 2026-09-18: 70
- 2026-09-17: 69
- 2026-09-16: 69
- 2026-09-15: 68
- 2026-09-14: 68
- 2026-09-13: 67
- 2026-09-12: 67
- 2026-09-11: 66
- 2026-09-10: 66

## Common questions

### What is the PrePublish - YouTube script QA MCP server?

PrePublish - YouTube script QA is an MCP server listed in the public MCP registry as ai.prepublish/script-audit. Audit a YouTube script before recording: hook, pacing, drop-off risk, copy-paste rewrites. This page covers its hosted endpoint (https://mcp.prepublish.ai).

### Is the PrePublish - YouTube script QA MCP server safe to use?

PrePublish - YouTube script QA scores 70 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 PrePublish - YouTube script QA MCP server expose?

PrePublish - YouTube script QA exposes 6 tools: audit_script, get_audit, audit_hook, check_authenticity, policy_preflight, script_runtime. Their descriptions and schemas cost roughly 1,215 tokens of context every time the server is loaded.

### Does the PrePublish - YouTube script QA MCP server require authentication?

No. We connected to PrePublish - YouTube script QA without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the PrePublish - YouTube script QA MCP server still maintained?

PrePublish - YouTube script QA is still listed as active in the MCP registry. We last reached this channel on 20 September 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://mcp.prepublish.ai/
- Website: https://prepublish.ai/mcp-server
- Changelog RSS feed: https://verifymcp.io/servers/ai-prepublish-script-audit/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-prepublish-script-audit/mcp.json
- HTML version of this page: https://verifymcp.io/servers/ai-prepublish-script-audit/mcp