Prepublish MCP vs Storelift
A side-by-side look at the Prepublish MCP and Storelift MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Prepublish MCPMarketing · Local subprocess (stdio)Audit YouTube scripts before recording: hook, structure and pacing scores, drop-off passages, policy and inauthentic-content checks, and runtime estimates.57GoodAuth: no auth requiredVerdict: choose Prepublish MCP for marketing work as a local process; choose Storelift for marketing as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Prepublish MCP when
- You need dedicated capabilities in the Marketing domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: No auth required.
- You want tools like
audit_script, get_audit, audit_hook.
Choose Storelift when
- You need dedicated capabilities in the Marketing domain.
- You prefer a local stdio subprocess transport.
- You have the keys it needs:
STORELIFT_API_KEY, STORELIFT_API. - You want tools like
list_apps, get_keywords, get_rivals.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | Prepublish MCP | |
|---|---|---|
| Category | Marketing | Marketing |
| Quality signal | 57/100 · Good | 61/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | No auth required | Not declared |
| Pricing | Not declared | Not declared |
| Required env vars | None listed | STORELIFT_API_KEYSTORELIFT_API |
| 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 | 8 |
| Full listing | View Prepublish MCP | View Storelift |
Tools & capabilities
Prepublish MCP tools 6
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 videos
Storelift tools 8
list_appsList the apps tracked in this Storelift account (id, name, countries, keywords). Call this first — every other tool needs an appId from here.get_keywordsKeyword ranks for one app in one App Store / Google Play country. THREE STATES ARE DISTINCT: measured=false means the query could not be measured, rank=null means it was measured but the app is absent from the top results, rank=<number> is the rank. Never collapse them into one — counting an unmeasured day as zero produces a false answer.get_rivalsApps that rank ABOVE this app in search. For each rival you get the keywords it beats you on, its rank there (theirRank) and yours (ourRank) — ourRank null means the app does not appear for that keyword at all.get_ai_visibilityWhether AI assistants name this app when asked natural questions about its category — reported per engine (Claude / ChatGPT / Gemini), never averaged. This is an OBSERVATION, not a ranking: a model's knowledge is frozen at a date and the answer is not identical every time, so read the trend rather than a single measurement.get_historyKeyword rank history for one country. Series points are [day, rank]; a null rank means the app was absent from the top results that day, which is not the same as a bad rank.get_store_pageThe app's own store listing signals for one country: name, subtitle, version, in-app events, editorial placements, similar-apps shelves and the screenshot set (iOS), plus the Google Play page (exact install count, rating histogram, ad/IAP flags, chart badge). `timeline` lists the dated changes we detected on the listing — the cheapest explanation for a rank move. measured=false means the page was never read; it is not the same as an empty page.get_reviewsRecent reviews for one country: `list` is the App Store feed, `android` the Google Play page (a narrower window, and Play publishes no review title or version). `newCount` is how many arrived since the previous measurement — null means an older record where the field was never written, which is not zero. android=null means Play was never measured; an empty list means there genuinely are no reviews.get_chartsApp Store chart position for one country: current ranks per list (free / paid / grossing, overall and in category) plus their history. Google Play is absent on purpose — Google publishes no chart list, so there is nothing to read, and a number here would be invented.
Ready-to-paste client configs
Paste 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.
Prepublish MCP
{
"mcpServers": {
"prepublish-prepublish-mcp": {
"command": "npx",
"args": [
"-y",
"prepublish-mcp"
]
}
}
}
Storelift
{
"mcpServers": {
"storelift": {
"command": "npx",
"args": [
"-y",
"storelift-mcp"
],
"env": {
"STORELIFT_API_KEY": "YOUR_STORELIFT_API_KEY_HERE",
"STORELIFT_API": "YOUR_STORELIFT_API_HERE"
}
}
}
}
Frequently asked questions
Prepublish MCP is categorized under Marketing and uses a local stdio subprocess. Storelift belongs to Marketing and uses a local stdio subprocess. Pick Prepublish MCP for marketing work and Storelift for marketing.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Prepublish MCP has no declared pricing — check the project's own site. Auth: no auth required. Storelift has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add prepublish-prepublish-mcp and storelift as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Prepublish MCP has a quality signal of 57/100 (Good) with 0 views, 0 installs and 0 GitHub stars. Storelift has 61/100 (Good) with 3 views, 0 installs and 1 GitHub stars.