A side-by-side look at the Prepublish MCP and Token Meter MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Prepublish MCP for marketing work as a local process; choose Token Meter for marketing as a local process. You can also run both side by side in one mcpServers block.
audit_script, get_audit, audit_hook.usage_summary, recent_sessions, session_tools.Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Marketing | Marketing |
| Quality signal | 57/100 · Good | 60/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | No auth required | No auth required |
| Pricing | Not declared | Freemium |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 0 | 1 |
| Directory activity | 0 views 0 installs 0 upvotes | 3 views 0 installs 0 upvotes |
| Tools | 6 | 4 |
| Full listing | View Prepublish MCP | View Token Meter |
audit_scriptFull 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 idget_auditCollect an earlier audit by `analysis_idaudit_hookPer-sentence attention pull across the opening, curiosity gap, payoff distance, a grade, and rewritten alternativescheck_authenticityReused, templated or mass-produced content risk, with the quotes that fired each signalpolicy_preflightWhich YouTube policy families a script touches, each citing YouTube's own pagescript_runtimeWords to runtime and runtime to a word budget, at 160, 181 and 201 words per minute measured across 349 videosusage_summaryDaily table of token counts, USD-equivalent cost, and call counts — broken down by day and modelrecent_sessionsLatest sessions with paste-ready `claude --resume` / `codex resume` commandssession_toolsPer-tool breakdown inside a session: call count, total tokens, average latency, response sizerefresh_dataRe-scans your local JSONL logs for new activity, then returns a fresh summaryPaste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
{
"mcpServers": {
"prepublish-prepublish-mcp": {
"command": "npx",
"args": [
"-y",
"prepublish-mcp"
]
}
}
}
{
"mcpServers": {
"whdrnr2583-cmd-token-meter": {
"command": "npx",
"args": [
"-y",
"@whdrnr2583/token-meter"
]
}
}
}