Data to AI™ / Gemini/Apple Search Ads
Pull Apple Search Ads campaign and keyword data into scripts, CSVs and pull requests from the terminal, so app teams check paid installs around a release without opening the ads dashboard.
Better answers, fewer tokens.
Gemini CLI
Which countries brought installs at the lowest cost last month?
Canada had the lowest cost per install at $1.84, on a third of the UK's spend. The United States took the most budget at $2.61 per install.
| Country Or Region | Local Spend Amount | Total Installs | Total Avg CPI Amount |
|---|---|---|---|
| CA Report Campaigns | $3,120 | 1,696 | $1.84 |
| GB Report Campaigns | $9,480 | 4,190 | $2.26 |
| US Report Campaigns | $21,700 | 8,314 | $2.61 |
Figures come from Report Campaigns with Group By set to Country Or Region and a monthly breakdown, requested from Apple in UTC.
Apple Search Ads promotes iOS apps in App Store search results. Dataddo extracts three datasets: Campaigns with budgets and serving status, Report Campaigns with spend, taps, installs and cost per install by day, country or device, and Targeting Keywords Find with the bids and match types of one campaign.
Using the dataddo server, list every campaign Name from Campaigns with Status enabled and a Serving Status that is not running, with Serving State Reasons. Exit non-zero if the list is not empty.
A mobile engineer runs the check from the release script before an App Store update goes live, so paid traffic is not sent to a campaign that has quietly stopped serving.
Query Report Campaigns for the last 30 days by Date and Country Or Region and write Local Spend Amount, Taps, Total Installs and Total New Downloads to data/asa-daily.csv.
A data analyst commits the CSV next to the notebook that models install trends, and the pull request shows exactly which rows changed since last week.
Read Targeting Keywords Find and compare Text, Match Type and Bid Amount with bids/plan.yaml. Print keywords whose live Bid Amount differs from the plan.
A technical marketer keeps the intended bids in version control. Gemini Code Assist in VS Code shows where the live account drifted, and the fix is reviewed like any other change.
Data to AI™ is priced per seat, like the AI assistants your team already uses, with ~25% off on annual billing. Need tailored contracts or volume pricing? Talk to us about Enterprise.
Serve governed business data to Claude, ChatGPT and other AI tools over MCP.
$10.49/month
per seat
3 seats minimum
Flexibly deploy Dataddo in any cloud or hybrid environment.
Custom
We have a payment model that works for you
| Without Dataddo |
With Dataddo
|
Outcome for you | |
|---|---|---|---|
| Checks before a release | Nobody looks at the ads dashboard during a release, so a campaign that stopped serving is found days later in the weekly report. | Gemini CLI reads Serving Status from Campaigns in the release workflow and stops on any enabled campaign that is not running. | Serving checked at release |
| Data in the repo | Install figures are downloaded by hand and dropped into the repo with renamed columns and no record of the period. | Gemini CLI queries Report Campaigns through one MCP server and writes the same field names to the same CSV path on every run. | Reproducible install files |
| Bid changes | Bid edits in the Apple Search Ads dashboard leave no review trail, and the planned bids in a spreadsheet drift apart from the live ones. | Targeting Keywords Find returns every keyword with Bid Amount and Modification Time, so Gemini prints the drift against the plan file. | Bid drift visible in review |
| Token consumption | Gemini spends tokens exploring raw Apple Search Ads columns, sampling rows and retrying until it understands the data. | Field definitions and relations are supplied up front, so the model skips the exploration and goes straight to the answer. | Fewer tokens per answer |
| Answer quality | Prone to wrong joins, invented fields and numbers that are hard to check. | Answers grounded in defined fields. In the Dataddo benchmark, 78.5% of questions were answered correctly, against 65.5% with plain CSV files. | Better answers |
The Apple Search Ads datasets marketing teams use most, with their real field names. Gemini queries them by name through the Dataddo semantic layer.
| Dataset | Metrics and attributes |
Ask Gemini
|
|---|---|---|
| Report Campaigns |
|
Write Local Spend Amount, Total Installs and Total Install Rate per Country Or Region for the last 30 days to a CSV in the repo. |
| Campaigns |
|
List every campaign Name with Serving Status and Serving State Reasons, and fail the check if any enabled campaign is not running. |
| Targeting Keywords Find |
|
Export keyword Text, Match Type and Bid Amount to bids/current.csv so the diff against our bid plan shows in the pull request. |
We asked 43 pre-registered questions of three real datasets - Google Search Console, HubSpot deals and Google Ads - and delivered the same rows to the same model in four ways. Only the data layer changed.
of questions answered correctly - the best of the four delivery methods tested
fewer confidently wrong answers - 14.0% of runs against 24.0% and 26.3%
more correct answers on messy CRM data - better on 8 questions, worse on none
Same model, prompts and rows in every condition; 759 graded runs, ground truth frozen before any run. On Google Search Console alone, documented CSV files did as well as Data to AI™ - the advantage comes from messier data such as HubSpot deals.
Read the benchmark →Extract Apple Search Ads in Dataddo with Report Campaigns and Targeting Keywords Find and attach them to a Google Gemini destination or AI Model. Add Dataddo under mcpServers in ~/.gemini/settings.json with httpUrl https://headless.dataddo.com/mcp-data, restart Gemini CLI, run /mcp auth dataddo and sign in.
With url, Gemini CLI falls back to SSE, which Dataddo does not support. Add Dataddo under mcpServers with the httpUrl key and no headers or oauth block, restart Gemini CLI, run /mcp auth dataddo and check the server with /mcp.
Yes. Agent mode in VS Code reads the same settings.json as Gemini CLI. In IntelliJ, Gemini Code Assist uses its own mcp.json, so add the Dataddo server there.
Gemini CLI asks you to confirm each Dataddo tool call. You can choose Always allow per tool, which suits a check you run repeatedly. Sign-in still needs a web browser on the same machine.
Yes. Once signed in, Gemini reaches every flow or Context attached to an AI destination or AI Model in that Dataddo account, not only the Google Gemini ones. Use a separate Dataddo account if Apple Search Ads data should stay apart.
As fresh as the last scheduled extraction. Report Campaigns and Campaigns re-read a moving date window on each run, while Targeting Keywords Find pulls all current keywords of its campaign every time.
No. Gemini only reads data Dataddo extracted, through a read-only semantic layer that never accepts SQL from the model. Nothing is written back to Apple, so bid changes still happen in the Apple Search Ads account.
Credentials are stored in ~/.gemini/mcp-oauth-tokens.json and renewed automatically. If a session expires or is revoked, run /mcp auth dataddo again and sign in with your Dataddo email and password.
