Meta Ads and Google Ads in ChatGPT

Ask ChatGPT how this week compares with last week across every account of a client, which ads are fatiguing, or what the account's ROAS was over an exact period. performance_period and metric_compare read the figures at the account, campaign, ad set or ad level, campaigns_structure returns how an account is built, budget_recommend says whether each budget should be kept, raised, cut or investigated, and store_revenue sets Shopify or Stripe revenue next to spend. ChatGPT turns the tables into the note, the summary or the answer you asked for.

A launch starts with launch_brief, which lists what is still missing as questions with options. Once nothing is missing, campaigns_launch prepares the campaign, ad sets and ads on Meta, and google_ads_build prepares a Search, Display, Demand Gen or Performance Max campaign. A pause, a resume, a duplicate, a split test or a budget change of at most 30% is prepared as one exact change.

• Compare periods and accounts, with revenue next to spend
• Prepare a launch from a brief, built paused when it is applied
• Prepare pauses, budget moves and edits, applied from Adrails

ChatGPT adds remote MCP servers through Developer mode. Whether you can turn it on depends on your ChatGPT plan and your workspace's policy: OpenAI lists it for Pro, Plus, Business, Enterprise and Education accounts on the web. The server is added once, then enabled in the conversations where you want it.

ChatGPT asks you to confirm a write action before it runs. That is ChatGPT's own setting: an advertising change is still applied from its page in Adrails, never from the confirmation in ChatGPT.

• 1. In ChatGPT Settings, turn on Developer mode
• 2. Open Plugins and add a custom MCP server named Adrails, with https://adrails.ai/api/mcp as its URL and OAuth as its authentication
• 3. Sign in to Adrails, choose the workspace and the permissions, and choose Allow access
• 4. Review the tools ChatGPT discovered, then add Adrails to a new conversation

The server registers 63 tools: the 43 tools the Adrails agents use in the app and 20 tools for accounts, integrations, campaign drafts, automations, Knowledge and job status. ChatGPT discovers only the tools the connection's permissions and your role allow, and its app settings let you switch individual tools off and refresh the list from the server.

Every tool, its inputs and who can call it is in the MCP tools reference, and the server card lists each tool with the schema the server registers, marked read-only or not.

ChatGPT signs in to Adrails with OAuth 2.1: the client registers itself, and no client ID, secret or API key is copied. The consent screen asks for one workspace and the permissions you grant. Read workspace data is required and covers every ad account of that workspace; Prepare advertising changes is a separate permission that only an owner or admin can grant, and a permission never goes beyond your role.

No tool creates, edits, pauses, switches on or rebudgets a campaign, ad set or ad by itself. A change comes back with a link to the Review advertising change page in Adrails, where an owner or admin applies it or declines it after Adrails reads the platform again. Everything a launch creates lands paused, switching it on is a second proposal that lists every budget that starts spending, and an applied change can be undone while the platform still matches what Adrails wrote. A proposal expires after 30 minutes.

A tool result goes to ChatGPT and from there to OpenAI under its terms; results never contain provider credentials or Adrails tokens. Every tool call is recorded with who made it, the workspace, the client, the tool, the outcome and the duration. Revoke ChatGPT at any time under Your connections on the MCP page in Adrails; removing the server in ChatGPT does not revoke it there.