01
Compare performance without erasing context
Compare answers from supported advertising sources while keeping each source, period, currency, and attribution model intact.
Adstudio MCP
Connect your ad accounts to the AI you already use. Meet Adstudio MCP.
Bring your advertising stack into ChatGPT or Claude through one accountable connection layer. Ask once, follow the tool work, and keep every returned source scoped and visible.
One connection layer for your advertising stack.
Adstudio stack& more MCP layer
Ask your connected sources
What changed across my selected ad accounts this month?
Found the ad accounts you can access
Checked each source’s available capabilities
Read performance from the live MCP sources
Kept currencies and attribution settings separate
Adstudio MCP summary
Your selected sources are ready to compare, with each account and measurement context intact.
Live MCP reads: Google Ads · Meta Ads
Source-labelledRead-onlyAccount scoped
The source is part of the answer
One question. Every source stays accountable.
Adstudio makes separate bounded reads from the accounts you select. Your AI client can bring supported advertising sources into one conversation without turning different currencies, attribution windows, or provider semantics into one invented number.
The result stays useful because it stays specific: provider, selected account, period, currency, attribution, freshness, truncation, and unresolved coverage remain visible where relevant.
Grounded work, less context switching
The ad-account questions that need more than one tab.
02
Follow the structure behind a result
Move from a selected account into campaigns and child entities when a high-level number needs an explanation.
03
Review the creative attached to the work
Bring creative assignments into the same grounded investigation instead of switching between tabs and exports.
04
Work across the accounts you already own
A personal connection follows your current and future workspace memberships, while your role and Read permissions still apply.
Connection, with boundaries
Three deliberate steps.
A useful answer starts with a connection whose scope is clear.
- 01
Create a personal connection
In Adstudio Settings → MCP, create your personal connection.
- 02
Enable platform Read
Choose Google Ads and/or Meta Ads. Your Adstudio role remains the boundary.
- 03
Select before you ask
Discover accounts, then explicitly name the workspace, platform, and account for a scoped read.
Meet people where the question starts
Bring the same grounded layer to the client and provider you use.
Google Ads
Trace a performance result into campaign, ad group, and ad context.
ExploreMeta Ads
Review campaign, ad set, creative, attribution, and coverage context.
ExploreChatGPT
Turn a natural-language question into evidence-rich source reads.
ExploreClaude
Start with explicit account choice, then follow the evidence.
Explore Built to make the boundary visible
Answers carry their source with them.
OAuth protects the personal connection. Role and platform Read bounds remain in force, and returned results retain provider, account, period, currency, attribution, freshness, truncation, and unresolved coverage where relevant.
Explore MCP securityEvidence receipt
- Provider
- Named per result
- Account
- Explicitly selected
- Measurement
- Period, currency, attribution
- Freshness
- Reported with the read
FAQ
The details, when you need them.
The public endpoint is https://useadstudio.com/api/mcp. Current read-only tools: list_accounts, describe_capabilities, query_performance, get_entities, get_creatives.
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.
Remove your personal MCP connection in Adstudio Settings → MCP, then remove the connector from your AI client. If a returned scope looks wrong, stop using the connection and contact Support.
Adstudio MCP
Bring accountable answers into the conversation.
Connect once, choose the account you mean, and keep the source context attached to every result.