Ad Radar
REMOTE · APP.AD-RADAR.DEV · SCANNED OCT 14
Search winning Meta ads, the hooks brands are scaling, and swipe briefs, inside Claude.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security97
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token. View diagnostics → Pass
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
- The authorisation server supports Client ID Metadata Documents, the current MCP client-registration mechanism. View diagnostics → Pass
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability69
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 881 tokens (~146/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management30
- Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage86
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 58% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
How do I install the Ad Radar MCP server?
Ad Radar is a hosted endpoint at https://app.ad-radar.dev/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · app.ad-radar.dev
claude mcp add --transport http dev-ad-radar-ad-radar 'https://app.ad-radar.dev/api/mcp'
{
"mcpServers": {
"dev-ad-radar-ad-radar": {
"url": "https://app.ad-radar.dev/api/mcp"
}
}
} {
"servers": {
"dev-ad-radar-ad-radar": {
"type": "http",
"url": "https://app.ad-radar.dev/api/mcp"
}
}
} [mcp_servers.dev-ad-radar-ad-radar] url = "https://app.ad-radar.dev/api/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"dev-ad-radar-ad-radar": {
"type": "remote",
"url": "https://app.ad-radar.dev/api/mcp",
"enabled": true
}
}
} openclaw mcp add dev-ad-radar-ad-radar --url 'https://app.ad-radar.dev/api/mcp' --transport streamable-http
mcp_servers:
dev-ad-radar-ad-radar:
url: "https://app.ad-radar.dev/api/mcp" {
"McpServers": {
"dev-ad-radar-ad-radar": {
"Transport": "http",
"Url": "https://app.ad-radar.dev/api/mcp"
}
}
} assistant mcp add dev-ad-radar-ad-radar -t streamable-http -u 'https://app.ad-radar.dev/api/mcp'
{
"mcpServers": {
"dev-ad-radar-ad-radar": {
"type": "http",
"url": "https://app.ad-radar.dev/api/mcp"
}
}
} The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 13 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.
- 12 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 17 to 23. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.
- 10 Oct 26 +4
- Authorization: fail → pass ▲ security
- First check of Authorization: pass security
- Server version: 1.1.0 → 1.2.0 functional
- 7 Oct 26 +40
- Transport: unverified → pass ▲ security
- Injection markers: unverified → pass ▲ security
- First check of Judged manipulation: pass security
- Authorization: Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token. security
- Tool “get_ad” rewrote its description, which is the text the model reads security
- Tool “search_ads” rewrote its description, which is the text the model reads security
- Tool “winning_patterns” rewrote its description, which is the text the model reads security
- MCP protocol: unverified → pass ▲ functional
- Stability: unverified → 0.07 ▲ functional
- Tool coverage: unverified → 100 ▲ functional
- First check of Schema quality: fail functional
- First check of Destructive annotations: pass functional
- First check of Schema quality: fail functional
- First check of Tool coverage: 58 functional
- First check of Schema quality: good functional
- 3 Oct 26 36
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 14 Oct 2026 · Probed https://app.ad-radar.dev/api/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=app.ad-radar.dev | CN=YR1,O=Let's Encrypt,C=US | 30 Sept 2026 | 29 Dec 2026 | RSA 2048 | SHA256-RSA | 643d51ad8b1c7bff2f10e0c67858b7ae3d9 |
| SANs: app.ad-radar.dev | ||||||
| CN=YR1,O=Let's Encrypt,C=US (CA) | CN=Root YR,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | RSA 2048 | SHA256-RSA | a20253f15f2691c05dc1ce13b9bcca4e |
| CN=Root YR,O=ISRG,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | RSA 4096 | SHA256-RSA | f24b6d17f9d9ad7cb1c9fea78782699f |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of app.ad-radar.dev. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| dev. | present | 60074 | 8 | Verified |
| ad-radar.dev. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication Enforced and verified
The endpoint asked for a token and published valid RFC 9728 metadata describing how to get one.
| Result | Enforced and verified |
|---|---|
| Enforced | On tool calls |
| HTTP status | 200 |
WWW-Authenticate challenge Bearer realm="Ad Radar", resource_metadata="https://app.ad-radar.dev/.well-known/oauth-protected-resource/api/mcp", scope="mcp:read"
Bearer realm="Ad Radar", resource_metadata="https://app.ad-radar.dev/.well-known/oauth-protected-resource/api/mcp", scope="mcp:read"| Header | Value |
|---|---|
| strict-transport-security | max-age=63072000 |
| content-security-policy | default-src 'self'; script-src 'self' 'unsafe-inline' https://www.clarity.ms https://*.clarity.ms https://c.bing.com; style-src 'self' 'unsafe-inline'; img-src 'self' https://fbcdn.net https://*.fbcdn.net https://fbsbx.com https://*.fbsbx.com data: blob: https://www.clarity.ms https://*.clarity.ms https://c.bing.com; media-src 'self' https://fbcdn.net https://*.fbcdn.net https://fbsbx.com https://*.fbsbx.com blob:; font-src 'self' data:; connect-src 'self' https://www.clarity.ms https://*.clarity.ms https://c.bing.com; frame-src 'none'; worker-src 'self' blob:; manifest-src 'self'; object-src 'none'; base-uri 'self'; form-action 'self' https://checkout.stripe.com https://billing.stripe.com; frame-ancestors 'none' |
| x-content-type-options | nosniff |
| x-frame-options | DENY |
| referrer-policy | strict-origin-when-cross-origin |
Protected resource metadata
| Document | https://app.ad-radar.dev/.well-known/oauth-protected-resource/api/mcp |
|---|---|
| Retrieved | Yes |
| Resource | https://app.ad-radar.dev/api/mcp |
| Authorisation server | https://app.ad-radar.dev |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://app.ad-radar.dev/api/mcp | Verified | 200 | |
| http (plaintext) | http://app.ad-radar.dev/api/mcp | HTTPS enforced | 308 | https://app.ad-radar.dev/api/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
advertiser_hooks Advertiser hooks ~53
The 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.
| Name | Type | Req | Description |
|---|---|---|---|
| advertiserId | integer | yes | – |
No output schema declared.
No examples provided.
get_ad Ad details ~184
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.
| Name | Type | Req | Description |
|---|---|---|---|
| key | string | yes | adKey ("meta:<id>"), a bare id or a Meta Ad Library id |
No output schema declared.
No examples provided.
get_swipe_prompt Swipe prompt ~179
A 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.
| Name | Type | Req | Description |
|---|---|---|---|
| annotate | boolean | – | Mark the copy blocks inside the script when available (swipe only) |
| key | string | yes | adKey ("meta:<id>"), a bare id or a Meta Ad Library id |
| kind | string | – | – |
| niche | string | – | Angle or audience to lean into (swipe only) |
| product | string | – | Your product, the one the prompt is for |
No output schema declared.
No examples provided.
list_taxonomy Taxonomy ~49
The 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.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
search_ads Search ads ~336
Search 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 understand it; in the rows they are cut at 140 and 280 characters (get_ad has them whole). Every other value in a row is the same get_ad returns for that ad. spendEstimate is an ESTIMATE based on engagement, not real spend; spendLowerBound = it is a minimum ("at least").
| Name | Type | Req | Description |
|---|---|---|---|
| advertiserId | integer | – | – |
| categories | array | – | Advertiser vertical, e.g. health, pet |
| includePastWinners | boolean | – | Also include winners that are no longer running (archive) |
| limit | integer | – | – |
| media | string | – | – |
| minDays | integer | – | Minimum days running |
| page | integer | – | – |
| query | string | – | Free text over headline, body, advertiser name and transcript |
| sort | string | – | – |
| 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 |
No output schema declared.
No examples provided.
winning_patterns Winning patterns ~80
The '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.
| Name | Type | Req | Description |
|---|---|---|---|
| format | string | – | – |
No output schema declared.
No examples provided.
What is the Ad Radar MCP server?
Ad Radar is an MCP server listed in the public MCP registry as dev.ad-radar/ad-radar. Search winning Meta ads, the hooks brands are scaling, and swipe briefs, inside Claude. This page covers its hosted endpoint (https://app.ad-radar.dev/api/mcp).
Is the Ad Radar MCP server safe to use?
Ad Radar scores 82 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Ad Radar MCP server expose?
Ad Radar exposes 6 tools: search_ads, get_ad, get_swipe_prompt, list_taxonomy, advertiser_hooks, winning_patterns. Their descriptions and schemas cost roughly 881 tokens of context every time the server is loaded.
Does the Ad Radar MCP server require authentication?
Yes. Ad Radar asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.
Is the Ad Radar MCP server still maintained?
Ad Radar is still listed as active in the MCP registry. We last reached this channel on 14 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.