MCP tool reference

Twenty one tools, every one of them a GET annotated readOnlyHint: true. Almost all of them take an appId, which you get from list_apps.

Apps

Tool	Title	Returns	Parameters
`list_apps`	List apps	Every tracked app with its store, home country, latest visibility score and keyword count	None
`get_app`	Get app	Full detail for one app, including store metadata, home storefront, latest snapshot and category	`appId`
`app_summary`	App summary	Tracked keyword count, visibility, average position and recent movement	`appId`
`portfolio`	Portfolio summary	Cross app totals and per app visibility, keyword and movement figures	None

Start with list_apps. Nothing else works without an app id.

Keywords

Tool	Title	Returns	Parameters
`list_keywords`	List tracked keywords	Tracked keywords with traffic, difficulty and opportunity scores and the latest checked position	`appId`, `sort`, `country`
`keyword_suggestions`	Keyword suggestions	Suggested keywords from one strategy, without tracking anything	`appId`, `strategy`, `limit`, `country`

Keywords are per market, so pass country to scope to one storefront. strategy chooses the suggestion source: metadata, search, similar, developer, competitors, seasonal or reviews.

Insights

Tool	Title	Returns	Parameters
`ranking_history`	Ranking history	Daily position history over a date window	`appId`, `keywordIds`, `from`, `to`
`serp_snapshot`	SERP snapshot	The stored search results for one keyword on one day	`keywordId`, `date`
`serp_movers`	SERP movers	Keywords whose result order shifted most over the last N days	`appId`, `days`
`visibility_history`	Visibility history	Daily visibility score over a date window	`appId`, `from`, `to`
`rank_distribution_history`	Rank distribution history	Daily counts of keywords per rank band	`appId`, `from`, `to`
`ratings_history`	Ratings history	Daily average rating and rating count	`appId`, `from`, `to`
`app_audit`	ASO audit	The latest audit with per check findings and recommendations	`appId`
`audit_history`	Audit history	Historical audit scores over a date window	`appId`, `from`, `to`
`metadata_audit`	Metadata audit	Metadata lint and keyword coverage with character limit warnings	`appId`
`list_reviews`	List reviews	Recent store reviews, optionally filtered	`appId`, `score`, `version`, `limit`
`changes_timeline`	Changes timeline	Detected change events over the last N days, newest first	`appId`, `days`
`daily_budget`	Daily request budget	The estimated daily store request fan out against the configured limits	None

from and to are inclusive UTC date strings in YYYY-MM-DD form. Omit keywordIds on ranking_history to get every tracked keyword, and omit date on serp_snapshot to get the most recent one.

Actions

Tool	Title	Returns	Parameters
`list_actions`	List actions	The prioritized queue across every app, sorted by impact then age	`status`, `priority`, `rule`, `category`, `appId`, `country`, `store`, `limit`
`app_actions`	App actions	The prioritized queue for one app	`appId`, plus the same filters
`actions_summary`	Actions summary	Open and snoozed totals, counts per priority and category, and the most common rules	None

status defaults to OPEN and SNOOZED, and limit defaults to 100 with a maximum of 200. Actions exist only for tracked primary apps, never for competitors, which appear only inside evidence. See Work the Action Center.

Reading the results

Two conventions matter more than the rest when an agent is interpreting output. A position is 1 based, and null means the keyword was checked and the app was not found within that row’s depth. Never read null as zero. See Positions and rank depth. Apple and Google Play scores come from different public evidence and are not comparable, so never rank one store’s keyword against another’s. See App Store and Google Play.

Every tool maps to an endpoint

Each tool wraps one GET on the HTTP API, so the data an agent can reach is exactly the data the endpoint returns and nothing more. See asobeast API.

What is deliberately missing

There are no write tools. No tool imports, tracks, untracks, edits metadata, closes an action or queues a job. Mutations stay backlog behind an explicit opt in. Until then an agent proposes work and you decide.

​Apps

​Keywords

​Insights

​Actions

​Reading the results

​Every tool maps to an endpoint

​What is deliberately missing