apply_apple_ads_recommendation
THIS CHANGES WHAT A LIVE CAMPAIGN MAY SPEND, and it is the only tool in the Apple Ads suggestion/recommendation family that touches money. Applying a daily-budget recommendation raises that campaign’s daily budget to Apple’s suggested amount; applying a target-CPA recommendation moves the CPA its...
This record as markdown: /tools/hermoso/apply-apple-ads-recommendation.md
What apply_apple_ads_recommendation does on Hermoso
AI agents use apply_apple_ads_recommendation to create or update resources in Hermoso, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Hermoso environment.
Why apply_apple_ads_recommendation is rated Medium
An AI agent can call apply_apple_ads_recommendation faster than any human can review: one bad instruction and it creates or modifies resources in Hermoso by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
The rule that runs apply_apple_ads_recommendation safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Hermoso, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For apply_apple_ads_recommendation, this is the rule to start with:
apply_apple_ads_recommendation stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Hermoso, apply this rule, and every apply_apple_ads_recommendation call is checked against it from then on.
Questions about apply_apple_ads_recommendation
THIS CHANGES WHAT A LIVE CAMPAIGN MAY SPEND, and it is the only tool in the Apple Ads suggestion/recommendation family that touches money. Applying a daily-budget recommendation raises that campaign’s daily budget to Apple’s suggested amount; applying a target-CPA recommendation moves the CPA its auto-bidder chases. REQUIRES confirm:true, and the refusal you get without it is built from the recommendation READ BACK FROM APPLE — it names the campaign, states current -> recommended, and quotes Apple’s own projected spend at the new level — so you are confirming a specific change to a specific campaign rather than confirming that you pressed a button. Pass amount to apply a DIFFERENT number than Apple suggested; omit it to take Apple’s. The campaign’s STATUS IS NOT TOUCHED: this moves a ceiling, it never enables or pauses anything, and it does not make a paused campaign start spending. Only an AVAILABLE recommendation can be applied and applying is TERMINAL. The reply is confirmed by re-reading the CAMPAIGN, not by Apple’s acknowledgement. Free to call; the spending it enables is real. It is categorised as a Write tool in the Hermoso MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Hermoso MCP server in PolicyLayer and add a rule for apply_apple_ads_recommendation: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Hermoso. Nothing to install.
apply_apple_ads_recommendation is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the apply_apple_ads_recommendation rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for apply_apple_ads_recommendation. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
apply_apple_ads_recommendation is provided by the Hermoso MCP server (https://app.hermoso.ai/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Hermoso, and thousands of servers like it.
This server
Across the catalogue