INDIVIDUAL MCP TOOL

winning_patterns

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.

ad-radar.devnone authenticationAvailability not checked

LIVE ENDPOINT

https://app.ad-radar.dev/api/mcp

No auth detected

Connect to this endpoint to inspect the live schema for winning_patterns and invoke it with your own arguments.

Indexed input schema

{}

Risk classification

Inferred read-only · medium confidence · heuristic, not a guarantee.

No write-capable action terms were found; this is not proof that invocation has no side effects.

Parent server

ad-radar.dev

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.ad-radar]
url = "https://app.ad-radar.dev/api/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "ad-radar": {
      "type": "http",
      "url": "https://app.ad-radar.dev/api/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: ad-radar
Remote MCP URL: https://app.ad-radar.dev/api/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "ad-radar": {
      "url": "https://app.ad-radar.dev/api/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "ad-radar": {
      "type": "http",
      "url": "https://app.ad-radar.dev/api/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "ad-radar",
  "transport": "streamable-http",
  "url": "https://app.ad-radar.dev/api/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

Related tools

search_ads — Search the Ad Radar board: competitor ads from the Meta Ad Library, with the same filters as the board.
get_ad — 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.
get_swipe_prompt — A ready-to-run prompt for one ad.
list_taxonomy — 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.
advertiser_hooks — The hooks, hook mechanisms and angles an advertiser uses most, aggregated over all of its ads: the pattern worth swiping, not a single ad.