Ad Radar
Search winning Meta ads, the hooks brands are scaling, and swipe briefs, inside Claude.
Connect it
Settings → Connectors → Add custom connector
URL: https://app.ad-radar.dev/api/mcpSettings → Apps & Connectors → Advanced → Developer mode
Create connector with URL: https://app.ad-radar.dev/api/mcp{
"mcpServers": {
"ad-radar": {
"url": "https://app.ad-radar.dev/api/mcp",
"headers": {
"Authorization": "<YOUR_AUTHORIZATION>"
}
}
}
}claude mcp add --transport http ad-radar https://app.ad-radar.dev/api/mcp --header "Authorization: <value>"{
"servers": {
"ad-radar": {
"type": "http",
"url": "https://app.ad-radar.dev/api/mcp",
"headers": {
"Authorization": "<YOUR_AUTHORIZATION>"
}
}
}
}6 tools, verified live
search_adsread-onlySearch the Ad Radar board: competitor ads from the Meta Ad Library, with the same filters as the board. By default only ACTIVE ads, sorted by score. Returns compact rows with an adKey: call get_ad for the full record and get_swipe_prompt for a ready-to-run prompt. Call list_taxonomy first for valid tag values. headline and body can be null when the ad's text isn't available: use the tags to unders
get_adread-onlyFull record of one ad: headline, body, CTA, full transcript, metrics, spendEstimate (an ESTIMATE based on engagement, not real spend; spendLowerBound = it is a minimum, "at least"), delivery status, winnerObservation (when we first observed it above $50k), media (public URLs), links (post, Ad Library, landing page, board), tags (the same dimension and slug search_ads shows), publisher platforms an
get_swipe_promptread-onlyA ready-to-run prompt for one ad. kind='swipe' = rebuild the ad for your product: map its beats, check the fit, write a full version with the same structure, plus alternative hooks. kind='analysis' = why the ad works (audience, funnel, psychology, weak spots) and how to apply it to your business. Pass product to fill it in, then follow the returned prompt.
list_taxonomyread-onlyThe board's taxonomy dimensions (awareness, angle, hook_pattern, vformat, pformat, landing...) with their valid values: the slugs to use in the tags filter of search_ads.
advertiser_hooksread-onlyThe hooks, hook mechanisms and angles an advertiser uses most, aggregated over all of its ads: the pattern worth swiping, not a single ad. advertiserId comes from search_ads.
winning_patternsread-onlyThe 'What to do now' block of the analytics page: for each taxonomy value, how many times more often it produces winners than average (lift), with adoption (ads, advertisers) and example ads. doThis = above average, lower = below. exampleAdKeys are adKeys: pass them to get_ad.
Alternatives in Search & Research
Compare →SSSEO SkillA
Free Google Search Console MCP: your real GSC, Google Analytics and keyword data for AI agents.
GitHitsA
Search public open-source code, documentation, metadata, vulnerabilities, changelogs, and examples.
CMClinicaltrialsgov MCP ServerA
Search ClinicalTrials.gov: find studies, retrieve results, match patients to candidate trials.
ESG Hub MCP ServerA
ESG knowledge base for AI agents: hybrid search, glossary, frameworks, industries, graph traversal.
pmndrs docsA
Search and read the docs and examples of react-three-fiber, drei, zustand, jotai... from your agent
PMPubmed MCP ServerA
Search PubMed/Europe PMC, fetch articles and full text (PMC/EPMC/Unpaywall), citations, MeSH terms.