ChatGPT + MCP

Bring live ad context into ChatGPT.

Connect Adstudio through OAuth, discover the accounts available to you, and turn a natural-language question into separate Google Ads and Meta Ads reads with their evidence still attached.

A ChatGPT question with its evidence attachedIllustrative sample data - not a live account.

Question

How did my selected Google Ads and Meta Ads accounts perform this month?

I will make separate bounded reads and name each provider, account, period, currency, attribution, freshness, truncation, and unresolved coverage.

Google Ads logo

Google Ads

bounded read

$18,420 spend | 4.1x ROAS

USD | Aug 1-31 | account attribution | refreshed 2m ago

Meta Ads logo

Meta Ads

bounded read

EUR 9,840 spend | 3.6x ROAS

EUR | Aug 1-31 | 7-day click | refreshed 3m ago

Evidence-rich comparison

The accounts can be discussed together, but their measurement contexts stay separate.

Google Ads live Meta Ads live OAuth Read-only Source-labelled

A conversation, backed by the account you named

The useful answer is the one that shows its work.

In ChatGPT, add the public Adstudio MCP endpoint, complete OAuth, and start by discovering your active workspace integrations. Choose the workspace, platform, and account explicitly before asking for a scoped read.

ChatGPT availability and menu labels vary by plan and rollout. Adstudio does not write to campaigns through this MCP, and it cannot provide data unavailable from the selected Google Ads or Meta Ads account.

Grounded work, less context switching

A better conversation begins with clear scope.

01

Ask in the language of the question

Start with a plain-language performance, entity, or creative question instead of building an export before the investigation begins.

02

Keep every source-labelled

ChatGPT can discuss separate provider reads together while account, currency, period, attribution, freshness, truncation, and coverage stay visible.

03

Stop for missing scope instead of guessing

When an account is not explicit, the public MCP asks for the boundary rather than selecting one on your behalf.

Connection, with boundaries

Three deliberate steps.

ChatGPT receives a useful answer only after the source account is clear.

  1. 01

    Create a personal connection

    In Adstudio Settings → MCP, create your personal connection.

  2. 02

    Enable platform Read

    Choose Google Ads and/or Meta Ads. Your Adstudio role remains the boundary.

  3. 03

    Select before you ask

    Discover accounts, then explicitly name the workspace, platform, and account for a scoped read.

FAQ

ChatGPT connection, with the details below the decision.

In ChatGPT, enable Developer mode under Settings → Security and login when it is available to your account. Add a custom connector or app with the public MCP endpoint, complete OAuth, then start with account discovery.

Use the public MCP endpoint, https://useadstudio.com/api/mcp, in your compatible AI client and complete OAuth. Start with account discovery before an account-scoped question.

Google Ads and Meta Ads are live today. The MCP compares separate, source-labelled reads; it does not treat provider metrics, currencies, attribution models, or periods as interchangeable.

Nothing. Every current public MCP tool is read-only. It does not create, edit, pause, or delete campaigns, ads, budgets, audiences, or other advertising objects.

Start with account discovery, then explicitly choose one workspace, platform, and account for every scoped call. The server never guesses an account on your behalf.

A personal connection reaches workspaces you are a member of now and in the future. Platform Read permission applies across those memberships and never exceeds your Adstudio role.

Adstudio MCP

Bring accountable answers into the conversation.

Connect once, choose the account you mean, and keep the source context attached to every result.

Privacy Policy·Terms of Service