research_ads

Active

declared in 1.0.0

Natural-language ad research: a Claude tool-use loop over Meta/Google/LinkedIn ad libraries + organic TikTok. Returns a summary + the found ads (with their served URLs). Spends LLM tokens + ScrapeCreators credits.

Parameters schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "query"
  ],
  "properties": {
    "brand": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "object",
          "properties": {},
          "additionalProperties": {}
        }
      ],
      "description": "brand name or profile object to tailor the research to; omit to use the workspace’s saved brand"
    },
    "query": {
      "type": "string",
      "description": "what to research, e.g. \"the longest-running protein-pancake ads on Meta\""
    }
  }
}

What this tool wraps· 0 endpoints

min confidence0.70 0.50

No endpoints wrapped at confidence ≥ 0.70.

Parent server

Hermoso

https://github.com/hermoso-ai/hermoso

1/7 registries

View full server →