Menu da documentação
Primeiros passos
O que é o Opus GrowthInício rápidoAdicione à sua IAComo funcionaSegurança e aprovaçãoCréditosPlanosPerguntas frequentesApps de IA
Todos os appsChatGPTClaudeGrokPerplexityClaude CodeCodexGemini CLIOpenClawCursorVS CodeWindsurfOutros MCPPlataformas de anúncios
Google AdsMeta AdsLinkedIn AdsMicrosoft AdvertisingTikTok AdsChatGPT AdsAgências e MCCFontes de dados
Search ConsoleGoogle AnalyticsYouTubeBusiness ProfileTag ManagerSites e SEO
AI ServerWordPressSEO IntelligenceFraude de cliquesReferência de ferramentas
Todas as ferramentasGoogle AdsMeta AdsTikTok AdsLinkedIn AdsMicrosoft AdvertisingChatGPT AdsSearch ConsoleGoogle AnalyticsYouTubeBusiness ProfileTag ManagerWordPressAI ServerSEO IntelligenceFraude de cliquesMulticanalConta e cobrançaIdioma
Create & Run Experiment
Creates and runs a Google Ads custom EXPERIMENT (A/B test with a traffic split) on an existing Search or Display campaign: a control arm (the original campaign) and a treatment arm (a draft copy that gets the change),…
- Tipo
- Faz alterações
- Créditos
- 3
- Plataforma
- Google Ads
- Aprovação
- Prévia primeiro, aplicado após sua aprovação
O que faz
Creates and runs a Google Ads custom EXPERIMENT (A/B test with a traffic split) on an existing Search or Display campaign: a control arm (the original campaign) and a treatment arm (a draft copy that gets the change), such as a different landing page (final URL) or ad text on a share of traffic.
Steps (one action each): 1. create — campaign_id, name, treatment_percent (1-99, default 50), optional start_date/end_date (YYYY-MM-DD). Creates the experiment in SETUP and the treatment draft campaign. Nothing serves yet. 2. set_final_url — experiment_id, new_final_url; optional ad_group_id (an ad group id of the ORIGINAL campaign) and/or old_final_url to limit which treatment ads change. Changes the landing page of the treatment ads only. replace_text — experiment_id, find_text, replace_text; optional ad_group_id. Replaces text inside the treatment RSA headlines/descriptions. 3. schedule — experiment_id. Starts the experiment on its start date (Google requires at least one change in the treatment first). • results — experiment_id. Control vs treatment clicks, impressions, CTR, conversions, cost and a significance test for CTR and conversion rate. Read-only. • status — experiment_id. Arms, split, draft/treatment campaign and the treatment ads with their final URLs. Read-only. To end, apply the winner (promote) or delete an experiment use list_experiments (action=end|promote|remove). Writes need confirm=true; confirm=false returns a preview. The original campaign is never edited by this tool; while the experiment runs Google locks its bidding/budget/targeting.
A descrição está em inglês porque é o texto oficial que sua IA vê.
MCP: manage_experiment
Como usar
Você não chama as ferramentas pelo nome. Escreva o que quer no ChatGPT, Claude ou outro assistente conectado ao Opus Growth; a IA escolhe esta ferramenta quando ela serve.
Parâmetros
| Nome | Tipo | Obrigatório | Padrão | |
|---|---|---|---|---|
| customer_id | string | Obrigatório | · | Google Ads customer account ID to query or change. Use the numeric ID returned by list_accounts; omit separators unless this tool explicitly says otherwise. |
| action | string | Obrigatório | · | create · set_final_url · replace_text · schedule · results · status · Requested action for the selected resource; choose one of the actions allowed by this schema. |
| campaign_id | string | Opcional | · | Exact campaign identifier to target. Use the ID returned by an Opus Growth list or create operation, not a display name. |
| experiment_id | string | Opcional | · | Exact experiment identifier to target. Use the ID returned by an Opus Growth list or create operation, not a display name. |
| name | string | Opcional | · | Human-readable name for the resource being created or updated. |
| treatment_percent | integer | Opcional | 50 | Treatment percent expressed as the percentage format required by this operation. |
| start_date | string | Opcional | · | Inclusive start date for the requested period, in the format required by this tool. |
| end_date | string | Opcional | · | Inclusive end date for the requested period, in the format required by this tool. |
| new_final_url | string | Opcional | · | New final url URL used by manage experiment. |
| old_final_url | string | Opcional | · | Old final url URL used by manage experiment. |
| ad_group_id | string | Opcional | · | Exact ad group identifier to target. Use the ID returned by an Opus Growth list or create operation, not a display name. |
| find_text | string | Opcional | · | Exact find text value for manage experiment. Supply text in the provider's required format; when it selects an existing resource, use the exact identifier returned by the relevant list or search operation. |
| replace_text | string | Opcional | · | Exact replace text value for manage experiment. Supply text in the provider's required format; when it selects an existing resource, use the exact identifier returned by the relevant list or search operation. |
| confirm | boolean | Opcional | false | Safety confirmation for a state-changing operation. Leave false to preview or validate; set true only after the user explicitly approves the shown change. |
Ferramentas relacionadas
account_auditAccount Snapshotaccount_snapshotAdd Keywordsadd_keywordsAdd Negative Keywordadd_negative_keywordAdd PMax Imagesadd_pmax_imagesApply Recommendationapply_recommendationBudget Pacing Alertsbudget_pacing_alertsCompetitor Adscompetitor_adsConnect Business Profileconnect_business_profile