RecipeMeta Ads
Build a creative analytics dashboard in Claude
Builds the Get MCP Ads Creative analytics template as a Claude dashboard: KPIs against an equivalent period the reader picks (previous period, same dates last year, last year matching weekdays or a custom start, always the same number of days), a leaderboard with thumbnails, comparisons, daily trends, fatigue signals and the full creative table, with a platform selector when several ad platforms are connected.
IntentA live creative report the team opens every week: which visuals carry the account, how they move and when they tire.
- 3
- Steps
- 1
- Tools
- 2
- Rules
- 1
- Failure modes
When to use it
Use it when
- Someone asks for a creative dashboard, a creative report they can keep, or a Motion-style creative analytics view in Claude.
- A weekly creative review the whole team should open without asking again.
Do not use it when
- A one-off question about one creative: answer in the conversation.
- Hosts without Claude's Dashboard artifact type: use get_creative_performance instead.
What it needs first
Required
Preconditions
- The organisation is on Team or Enterprise: ready-made dashboards are not offered on Free or Pro.
- The account is ticked in the dashboard, confirmed via list_accounts.
Inputs
window- Analysis window.Default: last 30 days.
Procedure
In order. Every tool named is one the gateway ships, and links to its reference.
Resolve the client's ad accounts (one per platform) and workspace by name with list_accounts.
Fetch the template for those accounts: datasets, filters, page files and hand-over.
Create a Dashboard artifact, write every document exactly as given in one batch, read its check, hand over with the lines given.
Decision rules
The observable condition, what it lets you conclude, and what takes the conclusion back.
When
The template refuses the account's source
Conclude
Say which sources it covers today and offer get_creative_performance in the conversation instead of a partial dashboard.
When
A reader sees a source fail to load
Conclude
Their own Get MCP Ads access decides: check that their connection covers this client's workspace before changing the dashboard.
Evidence every conclusion must carry
- Every figure carries its account, metric and window.
- Anything below a readable sample size is reported as unjudged, not as zero.
Where the agent stops
- The readout changes nothing. Any change it motivates goes through Safe Writes: preview, human confirmation, then apply.
How it goes wrong quietly
The cases where the analysis is wrong and still looks right. Read them before trusting a number.
- Editing the template's page or queries by hand loses the provenance of each figure: ask for changes by name instead.
What the answer contains
- 01Readout
- The figures, with windows and accounts named.
- 02Flags
- What deserves a deeper skill or a human decision.