Meta Ads in ChatGPT

Meta Ads is connected once in Adrails, under Ad accounts, by signing in with the Facebook profile that can access your Business Portfolio and switching on the ad accounts to work with. Adrails reads ad accounts, campaigns, ad sets, ads and their results, with the Pages and pixels an ad needs, and ChatGPT reaches the same data through the MCP server, with your sign-in and inside the one workspace you chose.

In ChatGPT, the Meta Ads reads come from 8 tools: reporting_overview, performance_period, performance_diagnose, campaigns_structure, creative_insights, budget_recommend, findings_review and launch_brief. The table above says what each one returns and gives a question to type as it is. Every result comes back twice, as exact data for the model and as a readable table for you, so a figure ChatGPT states can be traced to the call that produced it.

ChatGPT adds remote MCP servers through Developer mode, which depends on your ChatGPT plan and your workspace's policy. The server is added once, then enabled in the conversations where you want it, and ChatGPT's app settings let you switch individual tools off and refresh the list from the server.

Every client uses the same server URL, https://adrails.ai/api/mcp, and the same sign-in: ChatGPT registers itself, you sign in to Adrails, then choose the workspace and the permissions on the consent screen. Meta Ads needs nothing on the ChatGPT side, since it is already connected in that workspace under Ad accounts.

• 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

Ask in your own words: ChatGPT picks the tool, Adrails returns the figures, and ChatGPT's model does the reasoning, so a tool call uses no agent credit. Each result carries the exact data in structuredContent.result and the same figures as readable tables.

A question can be narrowed to some of the workspace's ad accounts with accountIds, never widened to accounts outside it. A result is at most 256,000 bytes, so a long period at the ad level is asked for in shorter ranges or one campaign at a time.

• How did my Meta accounts do last week compared with the week before?
• Which ads have run the longest on the same creative, and are they fatiguing?
• Prepare a 20% budget increase on my best campaign, with the figures behind it.

No tool creates, edits, pauses, switches on or rebudgets a campaign, ad set or ad by itself. In ChatGPT, campaigns_launch builds the campaign, ad sets and ads of a complete launch_brief, all paused; campaigns_change_budget raises or lowers a daily budget by an amount or a percentage, at most 30% in one change; campaigns_pause pauses a campaign, ad group or ad by the ID an earlier read returned.

Then campaigns_set_status pauses or resumes one entity and measures the result after 24 hours, 3 days and 7 days; campaigns_duplicate_to_draft duplicates a campaign paused, replacing one source ad with 3 to 5 copy variants if you ask; campaigns_split_test creates a split test from a running ad set or ad, with one to three new variants that change one variable, paused. Each of them returns a proposal: a preview of the exact change and a link to the Review advertising change page in Adrails, where you, signed in as an owner or admin of the workspace, apply it or decline it. Adrails reads Meta Ads again first and applies the change once, or blocks it if the entity moved in the meantime.

A launch is built paused, switching it on is a second proposal that lists every budget that starts spending, an applied change can be undone while the platform still matches what Adrails wrote, and a proposal expires 30 minutes after it is prepared. ChatGPT asks you to confirm a write action before it runs; that confirmation is ChatGPT's own setting, and the advertising change is still applied from its page in Adrails, never from the confirmation.

Read workspace data is required and covers every ad account of the workspace; Prepare advertising changes is a separate permission that only an owner or admin can grant, and a permission never goes beyond your role. A member who connects ChatGPT reads Meta Ads but sees no write tool.

Structure, findings and overviews come from the account's last synchronization, and performance_period reads an exact date range from Meta. accounts_list shows each account's last snapshot, and an owner or admin who granted Manage integrations can queue a refresh with meta_sync. If a change is refused for a missing permission, reconnect Meta from Ad accounts so it asks again for ads_management.

Calls on one connection run one at a time, at most 60 a minute per access token, and a connection works in the one workspace you chose at consent: to work in another, connect ChatGPT again and choose it. Revoke ChatGPT under Your connections on the MCP page in Adrails; removing the server in ChatGPT does not revoke it there.