Apple Ads for AI agents.
Stop paying for taps that never install. Your agent harvests the search terms that install, blocks the ones that only spend, and moves bids inside caps you set. You approve everything else.
✓The audit is free and read-only. Nothing in your account changes.
- asa_get_sync_status · synced 3h ago · 4 storefronts
- asa_get_optimization_plan · CPA $3.80 against a $3.20 band
- asa_discover_search_term_silos · 12 terms installing on Search Match
- asa_propose_add_keywords · 10 exact keywords · applied under your policy
- asa_propose_budget_change · +45% on Brand US · waiting for your approval
59
MCP tools
Every dashboard action, callable by your agent.
30%
Largest budget step without you
Anything bigger waits in your approval queue.
20
Auto-applied changes a day
The ceiling per account, in any rolling 24 hours.
0
AI credits per agent call
Your agent runs on your own Claude or ChatGPT plan.
[ 01 / 06 ]Agent + approval queue
Your agent proposes. Your policy decides.
Every change your agent makes is a proposal first, with what moves, from what to what, and the taps, installs and CPA that triggered it.
- Bounded fixes, like a negative keyword or ten new exact keywords, apply under the policy you set.
- Anything larger waits in the approval queue with the rule it tripped named on the card.
- Every proposal is re-checked when it applies. If the account drifted, it goes back to the queue.
- Applied changes revert in one click, from the state saved before anything moved.
[ 02 / 06 ]For your agent
Connect your agent in one command.
No API key to paste. Claude Code, Cursor, Codex and claude.ai use the same URL and sign in through the browser.
Then ask — "Which Search Match terms installed last week but aren't exact keywords yet?"
claude mcp add --transport http tapandscale https://tapandscale.com/api/mcp[ 03 / 06 ]The weekly loop
The harvest your agent runs every week.
The loop that compounds on Apple Ads, done every week instead of when someone remembers.
Discover
Search Match and broad keywords surface the terms people actually type.
Harvest
Terms that install move into exact-match keywords, with their own bids.
Block
The same terms go negative where they were found, so you stop paying twice.
Tune
Bids and budgets move toward your CPA band, inside the caps you set.
What stays true every week
- Apple's vocabulary: taps, installs, TTR, CPT and CPA, by storefront
- A written reason on every change
- One-click revert from the history page
- Nothing outside the policy you set
[ 04 / 06 ]Why Tap & Scale
Built for agents, not bolted on.
Getting data
Report calls against a live, rate-limited API
A synced warehouse, plus custom reports when you need them
Making a change
The change goes live the moment the agent sends it
A proposal, applied by your policy or your approval
Undoing a change
Rebuild the old settings by hand
One-click revert from the state saved before it moved
Knowing what happened
No change history from Apple at all
A ledger of every change, its reason, and who approved it
Strategy
Whatever the prompt says this time
Your daily spend goal and CPA band, read on every plan
[ 05 / 06 ]What your agent does
The whole account, not just reports.
It can read everything. Every change it makes is a proposal, logged with its reason.
Harvest search terms
Move Search Match terms that install into exact keywords, and block the ones that don't.
Work the optimization plan
Pacing against your spend goal, CPA against your band, and what to scale or fix.
Move bids and budgets
CPT bids, default bids, CPA goals and budgets, inside your caps.
Expand storefronts
Clone what works into new countries, staged for your approval.
Audit the account
A scored audit with a 30/60/90-day roadmap, read-only.
Report every week
A weekly report by storefront, with the changes made and why.
[ 06 / 06 ]Pricing
Priced on what you spend, not what you guess.
Move the slider to your monthly Apple Ads spend. Once you're connected we read the real figure from your synced account, not an estimate.
Free for agents
Read everything. Propose anything.
$0
No card. However many accounts you connect.
- A full audit: five areas scored, 90 days of trend
- Every read over MCP and the API, from any agent
- Proposals drafted and queued — nothing applies
- Free for as long as you stay read-only
Copilot
Per ad account. Approved changes apply.
$149 /mo
$49 + 1% of $10,000
1.5% of your spend, all in
- Bounded fixes apply themselves, nightly
- Everything larger queues for your approval
- Search-term harvesting into EXACT silos
- One-click revert on every applied change
- Full MCP access from Claude, Claude Code, or Codex
- Never bills over $499/mo
Spend is read from the account you connect, so your bill tracks what Apple charges you. Reads, the audit and every proposal are free, for you or your agent; Copilot is billed per ad account and is what lets approved changes apply.
Questions people ask us
Find the installs your keywords are missing.
Connect your agent, run the free audit, and approve the first harvest.