Content Tools

prepublish.ai

An MCP server that audits YouTube scripts for attention hooks, authenticity, and policy risks before recording.

2 endpoints12 known toolsFirst detected September 10, 2026Last detected September 10, 2026

ENDPOINT 1

https://prepublish.ai/mcp

No auth detected

MCP server metadata

Name: prepublish
Version: 1.0.0

Capabilities

tools

Server instructions

PrePublish audits a YouTube script the user has already written, before they record: hook, structure and pacing scores, the passages most likely to lose attention, and copy-paste rewrites. Use audit_script for a finished draft, audit_hook for an opening only, check_authenticity for reused-content risk, policy_preflight for monetisation risk, and script_runtime for length arithmetic. These are text-only checks of an unrecorded script: never present a score as a prediction of published retention, and never invent an email address when a tool asks for one.

Known tools 6

audit_script

Run PrePublish's full audit on a YouTube script the user has already written.

Inferred read-only

get_audit

Fetch the current state of an audit that was started earlier, using the analysis_id that audit_script returned.

Inferred read-only

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 the top issues and rewritten alternatives.

Inferred read-only

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 change.

Inferred read-only

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 verdict and flag counts.

Inferred read-only

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.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

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

Claude Code

.mcp.json

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

Claude Desktop

Settings → Connectors → Add custom connector

Name: prepublish
Remote MCP URL: https://prepublish.ai/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

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

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

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

Generic MCP

Client-specific MCP configuration

{
  "name": "prepublish",
  "transport": "streamable-http",
  "url": "https://prepublish.ai/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

ENDPOINT 2

https://mcp.prepublish.ai

No auth detected

MCP server metadata

Name: prepublish
Version: 1.0.0

Capabilities

tools

Server instructions

Known tools 6

audit_script

Run PrePublish's full audit on a YouTube script the user has already written.

Inferred read-only

get_audit

Fetch the current state of an audit that was started earlier, using the analysis_id that audit_script returned.

Inferred read-only

audit_hook

Inferred read-only

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 change.

Inferred read-only

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 verdict and flag counts.

Inferred read-only

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.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

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

Claude Code

.mcp.json

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

Claude Desktop

Settings → Connectors → Add custom connector

Name: prepublish
Remote MCP URL: https://mcp.prepublish.ai

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

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

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

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

Generic MCP

Client-specific MCP configuration

{
  "name": "prepublish",
  "transport": "streamable-http",
  "url": "https://mcp.prepublish.ai"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.