Returns the curated niche taxonomy (up to four levels, e.g. "Health > Exercise > Gym") with, for each category, its id, path, level, parent and how many active profiles are categorized under it including its sub-niches. Only categories with at least minProfiles profiles in their subtree are returned (default 5), so every id you get back yields a real result set. Pass a categoryId to search_outliers, search_profiles or niche_trends to scope them to the creators in that niche; the filter always covers the subtree. Free to call and cached, so call it at the start of a session and reuse the ids. Categories are assigned per creator by our categorizer (reviewed by hand for new niches), which makes this filter more precise than a keyword over captions: it catches creators whose captions are hashtag-only or not in English.
Every creator in the database is categorized into a curated niche tree, from broad domains like Health and Wealth down to specific niches like Glute Training or Houseplants. list_categories hands you that tree with profile counts, and its ids become the categoryId filter on the search and trend skills, so an agent can ask for "what is overperforming in home improvement this month" without guessing keywords.
Connect the Viral Outliers MCP server once and the list_categories tool becomes available to your agent alongside all other skills:
claude mcp add --transport http viral-outliers https://viraloutliers.com/api/mcp \
--header "Authorization: Bearer so_live_YOUR_KEY"In Claude.ai or ChatGPT, add a custom connector pointing at https://viraloutliers.com/api/mcp. Your agent then calls list_categories on its own whenever the task needs it.
| Name | Type | Description |
|---|---|---|
minProfiles | number | Only niches with at least this many profiles in their subtree (default 5). |
maxLevel | number | Only niches up to this depth, 1-4 (default 4). Use 2 for a compact picker. |
A flat list of categories, each with its id, full path, level (1 to 4), parent path, the number of active profiles under it including sub-niches, and the number assigned to exactly that path. Categories whose subtree holds fewer than minProfiles profiles are left out, so an id from this list always scopes to a real set of creators.
It is free, read-only and cached. Fetch it once per session, pick the level of detail you need (maxLevel 2 gives a compact picker of domains and sub-domains), and reuse the ids in search_outliers, search_profiles and niche_trends.
A keyword matches caption text, which fails for creators whose captions are hashtag-only or not in English, and cannot express a browse question like "what went viral in gardening this week". A category is assigned per creator from their bio and posts, so categoryId scopes a search to the creators of a niche regardless of how they caption. The strongest queries combine both: a categoryId for the audience and a keyword for the specific topic.
This skill is free and never spends credits.
Call list_categories, pick the category id for the niche, and pass it as categoryId to search_outliers. The filter covers the niche and all its sub-niches, and it combines with every other search filter.
Categories with fewer than minProfiles profiles under them are hidden so every id yields real results. Lower minProfiles to see thinner niches, or pick the parent niche, which always includes its children.
No. It is a free lookup table. Credits are spent only on the searches you run with the ids it returns.
Also available as a REST API endpoint.
Related topics: niche taxonomy · creator categories · search by niche · category filter API · social media niche list