cogny cliapp marketingfirst 15 calls free

apple search ads scriptable from Bash.

Pull Apple Search Ads campaign, keyword, and search-term reports, harvest converting search terms into targeting keywords, and flip campaign status — all from the shell over the Apple Search Ads MCP. No Ads API client or JWT signing to manage.

1. sign up, free for the first calls (uses your git email)npx @cogny/cli init --agent claude-code
2. see every Apple Search Ads toolcogny tools list
3. call any tool from bash, no MCP wiringcogny tools call mcp__Apple_Search_Ads__tool_get_campaign_report --input '{…}'

01two paths

you're a person

Apple Search Ads makes you open each campaign, read the search-terms report, and manually re-add winners as keywords. The CLI pulls the search-term report and adds the harvested keywords in two scriptable calls. Connect Apple Search Ads once in Cogny Solo and let your coding agent, or a scheduled loop, do the querying for you.

you're an agent

Sign yourself up with one command. The CLI issues a key, wires nothing, and exposes every Apple Search Ads tool over JSON-RPC. The first 15 calls are free.

npx @cogny/cli init --agent claude-code

02tools call

real Apple Search Ads tools.

Tool names as the Apple Search Ads MCP serves them. Send --input JSON, get JSON back. The payloads are illustrative.

mcp__Apple_Search_Ads__tool_get_campaign_report

Campaign-level performance over a date range.

cogny tools call mcp__Apple_Search_Ads__tool_get_campaign_report \ --input '{"org_id":"987654","campaign_id":"1122334455","start_date":"2026-05-01","end_date":"2026-05-31","granularity":"TOTAL"}'

example response

{
  "row": [
    {
      "metadata": {
        "campaignId": 1122334455,
        "campaignName": "US — Brand"
      },
      "total": {
        "impressions": 184320,
        "taps": 9120,
        "installs": 1842,
        "localSpend": {
          "amount": "4120.55",
          "currency": "USD"
        }
      }
    }
  ]
}

mcp__Apple_Search_Ads__tool_get_search_term_report

Search terms that triggered your ads, with installs and spend.

cogny tools call mcp__Apple_Search_Ads__tool_get_search_term_report \ --input '{"org_id":"987654","campaign_id":"1122334455","start_date":"2026-05-01","end_date":"2026-05-31"}'

example response

{
  "row": [
    {
      "metadata": {
        "searchTermText": "budget tracker app",
        "keywordId": 778899
      },
      "total": {
        "taps": 412,
        "installs": 88,
        "localSpend": {
          "amount": "210.40",
          "currency": "USD"
        }
      }
    },
    {
      "metadata": {
        "searchTermText": "expense planner",
        "keywordId": null
      },
      "total": {
        "taps": 190,
        "installs": 41,
        "localSpend": {
          "amount": "98.10",
          "currency": "USD"
        }
      }
    }
  ]
}

mcp__Apple_Search_Ads__tool_add_targeting_keywords
Harvest a winning search term into an exact-match keyword.
- cogny tools call mcp__Apple_Search_Ads__tool_add_targeting_keywords \ --input '{"org_id":"987654","campaign_id":"1122334455","ad_group_id":"5566778899","keywords":[{"text":"budget tracker app","matchType":"EXACT","bidAmount":{"amount":"1.50","currency":"USD"}}]}'
example response
```
{
  "data": [
    {
      "id": 990011,
      "text": "budget tracker app",
      "matchType": "EXACT",
      "status": "ACTIVE"
    }
  ]
}
```

03tools list

the rest of the surface.

A sample of the other Apple Search Ads tools. Run cogny tools list --json for every tool and its input schema.

mcp__Apple_Search_Ads__tool_list_acls
mcp__Apple_Search_Ads__tool_get_campaigns
mcp__Apple_Search_Ads__tool_get_ad_groups
mcp__Apple_Search_Ads__tool_get_keyword_report
mcp__Apple_Search_Ads__tool_get_targeting_keywords
mcp__Apple_Search_Ads__tool_add_campaign_negative_keywords
mcp__Apple_Search_Ads__tool_get_account_spend
mcp__Apple_Search_Ads__tool_update_campaign_status
mcp__Apple_Search_Ads__tool_search_geo_locations

04then a verdict

calls from a script. verdicts from cogny.

Every write is logged with who authorised it. Launches your agent makes (a new campaign, a new ad) become measured tickets automatically; for other changes, your agent offers to register them. Cogny measures each in your own data, three days later for ads and seven for content and SEO, and closes it as worked, partial, didn't work or inconclusive.

worked
Moved the number. Every measured win has a share card.
partial
Some of it did.
didn't work
On the record anyway, so it isn't proposed again.
inconclusive
Not enough data to call.

How the loop works

05questions

questions.

Is this an official Apple Search Ads CLI?: No — it is the Cogny CLI calling the Apple Search Ads MCP over the cogny-mcp-proxy. You authenticate once via Cogny (OAuth handled for you) and then call every tool from Bash. No Ads API certificate or signed JWT to manage.
Can I automate the search-term harvest loop?: Yes. Pull tool_get_search_term_report, filter for converting terms, then feed them to tool_add_targeting_keywords as EXACT keywords — and add the noise as negatives via tool_add_campaign_negative_keywords.
Can my coding agent use this without MCP setup?: Yes — that is the point. `npx @cogny/cli init --agent claude-code` issues a key, then `cogny tools call mcp__Apple_Search_Ads__tool_get_search_term_report --input ...` works from any shell. No /mcp wiring or restart needed.

06related

Building an agent? The full tool map for every server is one fetch: /cli/llms.txt

apple search ads, then a verdict.

Start free All CLIs