Ad Radar is an MCP server published by dev.ad-radar, hosted at app.ad-radar.dev. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 6 tools, including search_ads, get_ad, get_swipe_prompt, list_taxonomy, advertiser_hooks.
Search winning Meta ads with $50k+ in estimated spend, read hooks and scripts, and draft briefs.
40 connections through 4 shared values. Tap any node.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
Searches the Ad Radar library of Facebook and Instagram ads from the Meta Ad Library (every ad has at least $50k estimated spend), with the same filters as the Ad Radar board. By default it returns only active ads, sorted by score, as compact rows. Each row has an adKey, which get_ad and get_swipe_prompt accept. Valid tag dimensions and slugs are the ones list_taxonomy returns. headline and body are null when the ad's text isn't available (the tags still describe the ad); in rows they are cut at 140 and 280 characters, while get_ad returns them whole. Every other value in a row matches what get_ad returns for that ad. spendEstimate is an estimate based on engagement, not reported spend; spendLowerBound true means the value is a minimum ("at least").
| Parameter | Type | Description |
|---|---|---|
| page | integer | Page number, starting at 1 (results stop at 1,000 per query) |
| sort | string | Order: score (Ad Radar score), reactions, rpd (reactions per day), days (days running) or recent (newest first) |
| tags | object | Taxonomy filters: { "<dimension>": ["slug", ...] }. Different dimensions are ANDed, slugs within one are ORed |
| tier | string | winner = top 10% by score and running 21+ days; rising = growing. Every ad on the radar has at least $50k estimated spend |
| limit | integer | Rows per page, 1-50 |
| media | string | Creative type: video, image (image and carousel ads) or all |
| query | string | Free text over headline, body, advertiser name and transcript |
| minDays | integer | Minimum days running |
| categories | array | Advertiser vertical, e.g. health, pet |
| advertiserId | integer | Only ads of this advertiser (the advertiserId shown in search rows) |
| includePastWinners | boolean | Also include winners that are no longer running (archive) |
{
"name": "search_ads",
"title": "Search ads",
"description": "Searches the Ad Radar library of Facebook and Instagram ads from the Meta Ad Library (every ad has at least $50k estimated spend), with the same filters as the Ad Radar board. By default it returns only active ads, sorted by score, as compact rows. Each row has an adKey, which get_ad and get_swipe_prompt accept. Valid tag dimensions and slugs are the ones list_taxonomy returns. headline and body are null when the ad's text isn't available (the tags still describe the ad); in rows they are cut at 140 and 280 characters, while get_ad returns them whole. Every other value in a row matches what get_ad returns for that ad. spendEstimate is an estimate based on engagement, not reported spend; spendLowerBound true means the value is a minimum (\"at least\").",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"page": {
"type": "integer",
"default": 1,
"maximum": 200,
"minimum": 1,
"description": "Page number, starting at 1 (results stop at 1,000 per query)"
},
"sort": {
"enum": [
"score",
"reactions",
"rpd",
"days",
"recent"
],
"type": "string",
"default": "score",
"description": "Order: score (Ad Radar score), reactions, rpd (reactions per day), days (days running) or recent (newest first)"
},
"tags": {
"type": "object",
"description": "Taxonomy filters: { \"<dimension>\": [\"slug\", ...] }. Different dimensions are ANDed, slugs within one are ORed",
"additionalProperties": {
"type": "array",
"items": {
"type": "string"
}
}
},
"tier": {
"enum": [
"winner",
"rising"
],
"type": "string",
"description": "winner = top 10% by score and running 21+ days; rising = growing. Every ad on the radar has at least $50k estimated spend"
},
"limit": {
"type": "integer",
"default": 15,
"maximum": 50,
"minimum": 1,
"description": "Rows per page, 1-50"
},
"media": {
"enum": [
"video",
"image",
"all"
],
"type": "string",
"default": "all",
"description": "Creative type: video, image (image and carousel ads) or all"
},
"query": {
"type": "string",
"maxLength": 300,
"description": "Free text over headline, body, advertiser name and transcript"
},
"minDays": {
"type": "integer",
"minimum": 0,
"description": "Minimum days running"
},
"categories": {
"type": "array",
"items": {
"type": "string"
},
"description": "Advertiser vertical, e.g. health, pet"
},
"advertiserId": {
"type": "integer",
"description": "Only ads of this advertiser (the advertiserId shown in search rows)"
},
"includePastWinners": {
"type": "boolean",
"default": false,
"description": "Also include winners that are no longer running (archive)"
}
},
"additionalProperties": false
},
"annotations": {
"title": "Search ads",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Returns the full 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 and landing domain. The transcript is in English: when the ad runs in another language (e.g. Spanish), transcript is the English translation, translatedFrom names the language and transcriptOriginal holds the original script. Text fields are null when they aren't available for that ad; the links always point to the original.
| Parameter | Type | Description |
|---|---|---|
| key * | string | adKey ("meta:<id>"), a bare id or a Meta Ad Library id |
{
"name": "get_ad",
"title": "Ad details",
"description": "Returns the full 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 $50k), media (public URLs), links (post, Ad Library, landing page, board), tags (the same dimension and slug search_ads shows), publisher platforms and landing domain. The transcript is in English: when the ad runs in another language (e.g. Spanish), transcript is the English translation, translatedFrom names the language and transcriptOriginal holds the original script. Text fields are null when they aren't available for that ad; the links always point to the original.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"key"
],
"properties": {
"key": {
"type": "string",
"maxLength": 80,
"description": "adKey (\"meta:<id>\"), a bare id or a Meta Ad Library id"
}
},
"additionalProperties": false
},
"annotations": {
"title": "Ad details",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Returns a prompt template built from one ad, written for the user to run on their own product. The result is JSON with the template text in the template field. kind='swipe' is a template that maps the ad's beats, checks the fit with the user's product, drafts a full version with the same structure and adds alternative hooks. kind='analysis' is a template that breaks down why the ad works (audience, funnel, psychology, weak spots) and how its structure applies to a business. product and niche are written into the template; without product the template keeps a placeholder for it.
| Parameter | Type | Description |
|---|---|---|
| key * | string | adKey ("meta:<id>"), a bare id or a Meta Ad Library id |
| kind | string | swipe = rebuild the ad for another product; analysis = why the ad works |
| niche | string | Angle or audience for the template (swipe only) |
| product | string | The user's product, written into the template |
| annotate | boolean | Mark the copy blocks inside the script when available (swipe only) |
{
"name": "get_swipe_prompt",
"title": "Swipe prompt",
"description": "Returns a prompt template built from one ad, written for the user to run on their own product. The result is JSON with the template text in the template field. kind='swipe' is a template that maps the ad's beats, checks the fit with the user's product, drafts a full version with the same structure and adds alternative hooks. kind='analysis' is a template that breaks down why the ad works (audience, funnel, psychology, weak spots) and how its structure applies to a business. product and niche are written into the template; without product the template keeps a placeholder for it.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"key"
],
"properties": {
"key": {
"type": "string",
"maxLength": 80,
"description": "adKey (\"meta:<id>\"), a bare id or a Meta Ad Library id"
},
"kind": {
"enum": [
"swipe",
"analysis"
],
"type": "string",
"default": "swipe",
"description": "swipe = rebuild the ad for another product; analysis = why the ad works"
},
"niche": {
"type": "string",
"maxLength": 300,
"description": "Angle or audience for the template (swipe only)"
},
"product": {
"type": "string",
"maxLength": 500,
"description": "The user's product, written into the template"
},
"annotate": {
"type": "boolean",
"default": true,
"description": "Mark the copy blocks inside the script when available (swipe only)"
}
},
"additionalProperties": false
},
"annotations": {
"title": "Swipe prompt",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Lists the taxonomy dimensions of the Ad Radar library (awareness, angle, hook_pattern, vformat, pformat, landing...) with their valid values. These slugs are the values the tags filter of search_ads accepts.
No parameters.
{
"name": "list_taxonomy",
"title": "Taxonomy",
"description": "Lists the taxonomy dimensions of the Ad Radar library (awareness, angle, hook_pattern, vformat, pformat, landing...) with their valid values. These slugs are the values the tags filter of search_ads accepts.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {}
},
"annotations": {
"title": "Taxonomy",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Returns the hooks, hook mechanisms and angles an advertiser uses most, counted over all of its ads in the library. advertiserId is the advertiser id shown in search_ads rows.
| Parameter | Type | Description |
|---|---|---|
| advertiserId * | integer | Advertiser id from a search_ads row |
{
"name": "advertiser_hooks",
"title": "Advertiser hooks",
"description": "Returns the hooks, hook mechanisms and angles an advertiser uses most, counted over all of its ads in the library. advertiserId is the advertiser id shown in search_ads rows.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"advertiserId"
],
"properties": {
"advertiserId": {
"type": "integer",
"description": "Advertiser id from a search_ads row"
}
},
"additionalProperties": false
},
"annotations": {
"title": "Advertiser hooks",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Returns, for each taxonomy value, how many times more often it appears among winning ads than on average (lift), with adoption (ads, advertisers) and example ads; the same data as the 'What to do now' block of the Ad Radar analytics page. doThis lists the values above average, lower the values below. exampleAdKeys are adKeys that get_ad accepts.
| Parameter | Type | Description |
|---|---|---|
| format | string | Creative type the lift is computed on |
{
"name": "winning_patterns",
"title": "Winning patterns",
"description": "Returns, for each taxonomy value, how many times more often it appears among winning ads than on average (lift), with adoption (ads, advertisers) and example ads; the same data as the 'What to do now' block of the Ad Radar analytics page. doThis lists the values above average, lower the values below. exampleAdKeys are adKeys that get_ad accepts.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"format": {
"enum": [
"all",
"video",
"image"
],
"type": "string",
"default": "all",
"description": "Creative type the lift is computed on"
}
},
"additionalProperties": false
},
"annotations": {
"title": "Winning patterns",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Names, descriptions and schemas were written by the server and are shown as data.
Pattern matches on what the server declares. They show what it says it can do, not what it does.
None yet. Changes appear after a server's second daily check.