Skip to main content
Glama
PrePublish MCP server

PrePublish MCP server

Official

prepublish-mcp

Audit a YouTube script before you record it, from inside your AI client.

Prepublish is a remote MCP server. It reads a draft that does not exist as a video yet and returns hook, structure and pacing scores, the passages most likely to lose viewers, an inauthentic-content check, a YouTube policy pre-flight that cites YouTube's own published pages, and a words-to-runtime calculator built on measured speaking rates.

Every other YouTube MCP server fetches the transcript of a video that is already published. This one reads the script you have not filmed.

Free, anonymous, no API key, no account.

Install

ChatGPT: install the listed plugin, no configuration. chatgpt.com/plugins/plugin_asdk_app_6aba148dbb6c81918fbc261b405c0c1c, or open Plugins in the ChatGPT sidebar, search Prepublish, and select Install plugin. Works across plans on web, desktop and mobile. In ChatGPT the full audit renders as an inline report card; install from the directory rather than asking the chat to find it, then @Prepublish in a message.

Claude Code, one command:

claude mcp add --transport http prepublish https://mcp.prepublish.ai

Cursor, VS Code, Windsurf, Claude Code project scope, or anything that reads an mcpServers object:

{
  "mcpServers": {
    "prepublish": {
      "type": "http",
      "url": "https://mcp.prepublish.ai"
    }
  }
}

Claude Desktop: add a custom connector under Customize, then Connectors, and paste https://mcp.prepublish.ai.

Codex CLI, ~/.codex/config.toml:

[mcp_servers.prepublish]
url = "https://mcp.prepublish.ai"

Clients that can only launch a command use the stdio bridge in this repository. It needs Node 20 or newer and forwards to the same endpoint:

{
  "mcpServers": {
    "prepublish": {
      "command": "npx",
      "args": ["-y", "prepublish-mcp"]
    }
  }
}

Agents installing this on a user's behalf should read llms-install.md.

Check it worked

Ask for a runtime estimate: "Use prepublish to convert 1500 words into a runtime range." script_runtime is local arithmetic, never rate limited, and returns three estimates. If that answers, the connection is good.

Related MCP server: PureRank MCP Server

Tools

Tool

Cost

What it returns

audit_script

AI-backed

Full audit of a finished draft: hook, structure and pacing scores, an attention-risk map naming the passages most likely to lose viewers, and a rewrite. Returns the analysis and its id

get_audit

free

Collect an earlier audit by analysis_id

audit_hook

AI-backed

Per-sentence attention pull across the opening, curiosity gap, payoff distance, a grade, and rewritten alternatives

check_authenticity

AI-backed

Reused, templated or mass-produced content risk, with the quotes that fired each signal

policy_preflight

AI-backed

Which YouTube policy families a script touches, each citing YouTube's own page

script_runtime

free, local

Words to runtime and runtime to a word budget, at 160, 181 and 201 words per minute measured across 349 videos

audit_script asks for an email address, because the full audit is released by email. The other five do not.

What it does not do

Every AI-backed response carries the same notice, and it is worth stating here too. These checks are text-only. They map relative attention risk inside an unrecorded script. They do not measure or predict the retention a published video will get, and no output here is a forecast of views, watch time or revenue.

Nothing fetches a video, a transcript or a channel. Every tool reads text you pass it.

Limits

The free tier is published live at GET https://mcp.prepublish.ai, which returns a machine-readable server card with the current day's usage.

Limit

Default

AI-backed calls per UTC day, across the whole endpoint

100

AI-backed calls per caller per 10 minutes

6

script_runtime is local arithmetic and never counts against either.

A bearer token in PREPUBLISH_TOKEN raises the limits without changing the tool list.

When the daily cap is reached the tool returns an error that tells the model not to retry and names the web alternative for that day. Failures return the next action rather than a stack trace.

Transport and protocol

Streamable HTTP, stateless. Supported revisions: 2025-11-25, 2025-06-18, 2025-03-26, 2024-11-05. A client asking for a supported revision gets it back; anything else negotiates to the newest one implemented, and the negotiated revision is reported identically in the response header and in the initialize result.

The endpoint validates the Origin header. Requests without one, which is every non-browser client, are always served. A browser origin that is not prepublish.ai is refused with 403, as the transport specification requires. An unsupported MCP-Protocol-Version header is a 400.

Aliases: https://prepublish.ai/mcp and https://mcp.prepublish.ai/mcp serve the same handler.

Development

The server itself lives in the Prepublish web application, not in this repository. What is here is the stdio bridge and the conformance suite that holds the hosted endpoint to the specification.

npm install
npm run build
MCP_URL=https://mcp.prepublish.ai npm test

The suite drives the endpoint with the official MCP SDK client over Streamable HTTP, so the wire format is checked against the reference implementation rather than against our own assumptions. It covers the handshake, tool discovery, schema shape, both directions of script_runtime, unknown-tool errors, the server card, batching rejection, notification handling, protocol negotiation in both directions, Origin validation, protocol version validation, and the stdio bridge round trip.

One AI-backed test is skipped unless MCP_TEST_BILLABLE=1, because a real call costs money and writes a row.

PREPUBLISH_MCP_URL overrides the upstream endpoint for the bridge. The bridge adds and hides nothing: a test asserts its tool list equals the hosted one, so adding a tool on the server needs no release here.

Registry

Published to the official MCP registry as ai.prepublish/script-audit, a remote-only entry under the DNS-verified ai.prepublish namespace. See server.json.

M8ven Score

License

MIT. See LICENSE.

Available Tools

6 tools
audit_hookScore the opening of a YouTube scriptA

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.

Inputs: hook_text (required), email, niche.

audit_scriptAudit a YouTube script before recordingA

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.

Inputs: script_text (required), video_title (required), email, audience, +2 more.

check_authenticityCheck a script for reused or inauthentic content riskA

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.

Inputs: script_text (required), video_title (required).

get_auditCollect a Prepublish audit by idA
Read-only

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.

Inputs: analysis_id (required).

policy_preflightPre-flight a script against YouTube advertiser and monetisation policyA

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.

Inputs: script (required), title.

script_runtimeConvert script length to spoken runtimeA
Read-only

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.

Inputs: word_count, script_text, target_minutes.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.4/5.0

    Scored across 6 tools

    Disambiguation5/5

    Each tool targets a clearly separate function: full-script audit, hook-only audit, audit retrieval, authenticity check, policy preflight, and runtime conversion. The descriptions explicitly state when to use each, so an agent is unlikely to confuse them.

    Naming Consistency4/5

    Most tools follow a verb_noun pattern like audit_script, audit_hook, get_audit, and check_authenticity, but policy_preflight and script_runtime are noun-first exceptions. The names remain readable and predictable overall, with only minor deviations.

    Tool Count5/5

    Six tools is well within the ideal range and each tool earns its place by covering a distinct pre-publish analysis need. There is no bloat or redundancy.

    Completeness5/5

    The toolset covers the full lifecycle implied by its purpose: creating full or hook audits, retrieving prior audits, and performing supporting checks for authenticity, policy, and runtime. No significant dead ends or missing operations are apparent.

    Maintenance

    ActivitySlowing
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      Provides AI agents with structured short-form content mechanics including hooks, script structures, retention strategies, and CTAs, along with auditing tools to avoid common posting failures.
      7
      48 npm
      1
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI agents to score drafts for AI-content-spam risk before publishing and scan entire sites, providing a pre-publish QA gate with pass/warn/fail verdicts.
      6 npm
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Checks AI-generated social media and ad content against current policies of 8 major platforms, flagging risky phrases and providing compliant rewrites to prevent account restrictions.
      1
      39 npm
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables MCP clients to query YouTube channel health, diagnose video performance, full-text search transcripts, and vet topics/scripts directly from an editor or chat interface.
      Apache 2.0