An agent can connect on its own if it already holds rankcusp_api_key.Remote endpoint behind a static API key or header. The registry never sees the value; the agent fills the placeholder.
tools.schemasevery tool has an object input schema
pass
tools.annotations9 of 9 tools declare readOnlyHint or destructiveHint
fail
tools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: list_keywords (openWorldHint); get_keyword (openWorldHint); audit_metadata (openWorldHint); …
pass
tools.token_costabout 1,374 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump
stability100 · weight 15
pass
stability.changesno tool changes in 30 days
pass
stability.rug_pullno tool changed its meaning under the same name
dependenciesn/a · weight 15
n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package
9 tools, about 1,374 tokens to load them all · tool set 9c5e1a384d00 · checked 2026-10-20 10:03 UTC
Tool changes
No tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.
Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.
Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.
Endpoints
remote
auth
reachable
uptime 30d
p50
protocol
last ok
https://rankcusp.com/api/mcpstreamable-http
api_key ${rankcusp_api_key}
yes
100%
724 ms
2025-06-18
2026-10-20
Tools (9)
add_keywords
Adds keywords to an app's tracked set in one storefront. Takes a list or a comma-separated paste. They arrive unscored - scoring costs requests to Apple and happens on the collector's schedule - so do not read a null popularity here as a zero.
audit_metadataread-only
Audits a draft title, subtitle and 100-character keyword field against Apple's rules and against each other. Returns what is wasted, what Apple will actually index, and the field rewritten without the waste. Nothing is submitted anywhere - this only reads the text you pass in.
country_prioritiesread-only
Ranks the storefronts an app is tracked in by how much is winnable there: how many keywords sit in the cusp band, how many already reach the top ten, and whether the rivals' ratings leave an opening. Answers which market to work on first.
cusp_actionsread-only
The keywords in the 11-30 band, ordered by popularity. The work list a metadata edit pays off on most.
get_keywordread-only
One keyword: its rank, its scores, its first page and the verdict - should it be targeted, and why. Every unmeasured value comes back null, never zero.
keyword_competitorsread-only
Who ranks for a phrase, deeper than the ten the first page carries. Use it to find the rivals a first-page reading misses - an app at 40 for a phrase you sit at 60 for is the one to study.
list_appsread-only
Lists the apps and rivals tracked on the account. The appId and storefront codes the other tools want come from here.
list_keywordsread-only
Lists an app's keywords in one storefront, with rank, popularity and difficulty.
ranking_keywordsread-only
Which keywords an app is already ranking for, from the pooled record of every search this product has run. Works on any App Store id, not only the ones on this account - point it at a rival to read theirs. Apple publishes no endpoint for this; the answer is only as wide as what has been observed, so an app nobody has swept near returns little.