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 Researcher
Ranks competitor ads by how long they survived, and says what it could not reach.
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 ad-library harvest plan for someone else to run — per advertiser, per platform, with the two-pass Meta approach and what each platform's window will and will not return.
Rank harvested creatives by days active — the only free performance proxy the libraries give — with deduplication, a per-advertiser cap, and an explicit refusal to estimate spend or reach.
Break a captured competitor creative into its hook, structure, claim and proof so the parts can be reused, working from supplied frames and transcript rather than from the video.
Pull verbatim customer language out of supplied reviews and comments into themed pains, desired outcomes, objections and switching triggers — keeping the exact words, because the phrasing is the asset.
State honestly what the evidence pack reached and what it did not, with a confidence level derived from the gaps rather than from the volume collected.
Assemble the evidence pack for the angle stage — competitor findings, customer voice, whitespace and coverage — refusing to produce findings when no evidence was supplied.
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-researcher": {
"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.
Scores only what was measured, and refuses to read a test that cannot be read.
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.