# create_openai_ads_campaign Build a campaign on the connected ChatGPT Ads account — the ads that appear below ChatGPT answers. ALWAYS created PAUSED at every level, with no override: it spends NOTHING until you activate it with set_openai_ads_status(confirm:true). The object graph is campaign -> ad group -> ad, and a campaign ON ITS OWN CANNOT SERVE AN IMPRESSION, so pass adGroup{name, maxBid, contextHints, ad{creative}} and this builds the whole tree. THE CREATIVE IS A TEXT + IMAGE CARD AND NOTHING ELSE — title 3–50 characters, body 100 maximum, one landing page, one still image. THERE IS NO VIDEO ON THIS CHANNEL: never offer a video ad here, and if the brand only has video, pull a frame from it first. TARGETING IS SEMANTIC: context hints are natural-language descriptions of the conversations where this ad belongs (up to 2,000 per ad group). Geo (countries / locationIds) and PLATFORMS (which of the iOS app, Android app and web the ad runs on) are the only other dimensions — leave platforms out to run on all three. They guide matching, they are NOT exact-match keywords, and they do not guarantee delivery. OpenAI’s own guidance is BREADTH — many genuinely distinct hints and many distinct title/body angles beat one message repeated — which is exactly what plan_variations and mine_angles produce. OpenAI has no atomic multi-object write available here, so the whole tree is VALIDATED before the first write; if a level below the campaign is still rejected, the campaign is left PAUSED (spending nothing) and the note says exactly what exists — nothing is archived behind your back, because archiving is irreversible. Everything is READ BACK from OpenAI before you are told it exists: print the returned note verbatim, and if it says the campaign cannot serve yet, say that rather than calling it a finished ad. Agent View of the PolicyLayer registry record for `create_openai_ads_campaign`. HTML page: https://policylayer.com/tools/hermoso/create-openai-ads-campaign ## Facts - Tool: `create_openai_ads_campaign` - Server: Hermoso (`https://app.hermoso.ai/mcp`) — https://policylayer.com/tools/hermoso.md - Homepage: git+https://github.com/hermoso-ai/hermoso.git - Risk category: Destructive (Critical risk) - Registry record: grade D, identity unverified - Server auth posture: gated - Server CORS policy: * - Server rate-limited: no - Parameters: 0 - Recommended policy verdict: Hidden ## Example call (MCP tools/call, JSON-RPC 2.0) ```json { "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "create_openai_ads_campaign", "arguments": {} } } ``` ## Why create_openai_ads_campaign is rated Critical An AI agent that decides to call create_openai_ads_campaign doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from Hermoso is gone. There is no undo for destructive operations. ## Use case AI agents call create_openai_ads_campaign to permanently remove resources in Hermoso, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo. ## Recommended policy (PolicyLayer) Verdict: **Hidden**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Hermoso: ```json { "version": "1", "default": "deny", "hide": [ "create_openai_ads_campaign" ] } ``` ## Other tools on Hermoso (895) - `answer_google_business_question` — Destructive — https://policylayer.com/tools/hermoso/answer-google-business-question.md - `apple_ads_change_history` — Destructive — https://policylayer.com/tools/hermoso/apple-ads-change-history.md - `associate_linkedin_conversion_campaigns` — Destructive — https://policylayer.com/tools/hermoso/associate-linkedin-conversion-campaigns.md - `cancel_openai_ads_audience_operation` — Destructive — https://policylayer.com/tools/hermoso/cancel-openai-ads-audience-operation.md - `cancel_scheduled` — Destructive — https://policylayer.com/tools/hermoso/cancel-scheduled.md - `cancel_stripe_subscription` — Destructive — https://policylayer.com/tools/hermoso/cancel-stripe-subscription.md - `clear_sheet_range` — Destructive — https://policylayer.com/tools/hermoso/clear-sheet-range.md - `create_analytics_custom_dimension` — Destructive — https://policylayer.com/tools/hermoso/create-analytics-custom-dimension.md - `delete_analytics_key_event` — Destructive — https://policylayer.com/tools/hermoso/delete-analytics-key-event.md - `delete_apple_ads_object` — Destructive — https://policylayer.com/tools/hermoso/delete-apple-ads-object.md - `delete_bluesky_post` — Destructive — https://policylayer.com/tools/hermoso/delete-bluesky-post.md - `delete_brand` — Destructive — https://policylayer.com/tools/hermoso/delete-brand.md - `delete_creator` — Destructive — https://policylayer.com/tools/hermoso/delete-creator.md - `delete_dm_automation` — Destructive — https://policylayer.com/tools/hermoso/delete-dm-automation.md - `delete_drive_file` — Destructive — https://policylayer.com/tools/hermoso/delete-drive-file.md - `delete_google_ads_object` — Destructive — https://policylayer.com/tools/hermoso/delete-google-ads-object.md - `delete_google_business_post` — Destructive — https://policylayer.com/tools/hermoso/delete-google-business-post.md - `delete_instagram_dm_automation` — Destructive — https://policylayer.com/tools/hermoso/delete-instagram-dm-automation.md - `delete_linkedin_ads_object` — Destructive — https://policylayer.com/tools/hermoso/delete-linkedin-ads-object.md - `delete_linkedin_comment` — Destructive — https://policylayer.com/tools/hermoso/delete-linkedin-comment.md - `delete_linkedin_lead_subscription` — Destructive — https://policylayer.com/tools/hermoso/delete-linkedin-lead-subscription.md - `delete_merchant_data_source` — Destructive — https://policylayer.com/tools/hermoso/delete-merchant-data-source.md - `delete_merchant_product` — Destructive — https://policylayer.com/tools/hermoso/delete-merchant-product.md - `delete_messenger_marketing_campaign` — Destructive — https://policylayer.com/tools/hermoso/delete-messenger-marketing-campaign.md - `delete_meta_audience` — Destructive — https://policylayer.com/tools/hermoso/delete-meta-audience.md - `delete_meta_catalog` — Destructive — https://policylayer.com/tools/hermoso/delete-meta-catalog.md - `delete_meta_object` — Destructive — https://policylayer.com/tools/hermoso/delete-meta-object.md - `delete_microsoft_ads_object` — Destructive — https://policylayer.com/tools/hermoso/delete-microsoft-ads-object.md - `delete_microsoft_merchant_product` — Destructive — https://policylayer.com/tools/hermoso/delete-microsoft-merchant-product.md - `delete_onedrive_file` — Destructive — https://policylayer.com/tools/hermoso/delete-onedrive-file.md - …and 865 more: https://policylayer.com/tools/hermoso.md ## For agents This record is a snapshot. Live verdicts and the full registry: - Check every server in your MCP config at once: `npx -y policylayer stack` - Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md) - Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events` --- Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=hermoso · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/hermoso