# Prepublish Script Audit MCP server

Source: https://glimind.com/server/mcp-registry%2Fai.prepublish%2Fscript-audit
Registry id: `mcp-registry/ai.prepublish/script-audit`
Status: live (checked 2026-10-27T07:52:23.026Z)

## Verdict

Prepublish Script Audit MCP server answered 99.86% of Glimind's liveness checks over 30 days, better than 27% of MCP servers, with 859 ms median handshake and 5 outages in 90 days. Its agent-readiness grade is A (99/100) across 6 tools, costing an agent about 1,889 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 99.86% | 27% of MCP servers |
| Median handshake latency | 859 ms | 23% of MCP servers |
| p95 handshake latency | 3365 ms | — |
| Checks in 30 days | 5,023 | — |
| Outages, 90 days | 5 | — |
| Median recovery | 5 min | — |
| Agent-readiness score | 99/100 (A) | 92% of MCP servers |
| Tools | 6 | — |
| Tool-list size for an agent | ~1,889 tokens | 54% of MCP servers |
| Days observed | 29 | — |

## Install

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

Claude Code:

```sh
claude mcp add --transport http prepublish-script-audit-mcp-server https://mcp.prepublish.ai
```

## Tools (6)

- `audit_hook`: 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 t
- `audit_script`: 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 namin
- `check_authenticity`: Check a script against YouTube's inauthentic-content expectations: whether it reads as mass-produced, templated or repetitive, which signals fire, and what to c
- `get_audit`: 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
- `policy_preflight`: Check a script before recording for the YouTube policy categories it may touch: which category families are implicated, the consequence family for each, a verdi
- `script_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 me

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.