Plans an install ad that only claims what the product actually did.
Early AccessEvery agent is free to connect — no card, no checkout.
We use essential cookies to keep you signed in. With your consent we also use non-essential cookies for analytics. Read our privacy policy
Browse › Marketing & Growth › Marketing Ad Tester
Scores only what was measured, and refuses to read a test that cannot be read.
A preview derived from this agent’s definition — not a live run. Nothing runs and no key is sent until you connect. FindAgent runs it on the hosted connection.
Write the exact measurement commands QA needs for a set of clips, and say which dimensions those measurements can and cannot settle.
Score one clip against its spec on the six dimensions, from supplied measurements and frames only, returning not-reviewed for anything the material cannot settle.
Structure the test so exactly one variable moves per cell and each cell can reach a readable result inside the budget and window.
Decide whether a test has accumulated enough to be read at all, and refuse the readout when it has not, rather than producing a direction from noise.
Read a completed test: what won, what died, what was attributable and what was not, separating a result from a difference that could be chance.
Turn a readout into the feedback that goes back to the angle, hook and script stages, so the next cycle starts from a result rather than from guesswork.
This MCP server runs on your own machine — FindAgent only points you at it. Run the command below, then add it to your MCP client. Nothing is hosted or proxied on our side.
npx -y @findagent/mcp runPaste this into your client config (e.g. claude_desktop_config.json or a Cursor mcp.json), then restart the client.
{
"mcpServers": {
"marketing-ad-tester": {
"command": "npx",
"args": [
"-y",
"@findagent/mcp",
"run"
]
}
}
}Plans an install ad that only claims what the product actually did.
Turns YouTube Analytics metrics into a deterministic performance narrative + recommendations
A 0–100 site health score from GA4, per device, with the failing metrics and what to do about each.
Ranks competitor ads by how long they survived, and says what it could not reach.
Scores ad angles with arithmetic you can audit, not a ranking you have to trust.
Shopify + Klaviyo segment analysis to target the highest abandoned-cart recovery opportunity
Flags the days your GA4 metrics deviate from their baseline — with the numbers computed, not guessed.
Maps your module graph, scores blast radius, plans migrations and composes a validated unified diff.
Turns a vague mobile feature request into a spec with a real scope boundary.