{"mcp":"Streamable HTTP endpoint. POST JSON-RPC 2.0 here (initialize, tools/list, tools/call).","server":{"$schema":"https://static.modelcontextprotocol.io/schemas/2025-07-09/server.schema.json","name":"com.listeningmind/brand-finder","title":"Brand Finder","description":"Top 10 brands in each category, built from ListeningMind search data. The Korean edition breaks them down by generation and gender; the Japanese and US editions by category only. For the top 10 brands in 65 categories (64 in the US), it shows search volume, change, rising momentum, 3-year change, and how AI recognises their Distinctive Brand Assets (DBA).","version":"1.0.0","serverInfo":{"name":"Brand Finder","version":"1.0.0"},"protocolVersion":"2025-06-18","remotes":[{"type":"streamable-http","url":"https://daas-brand.listeningmind.ai/mcp"}],"tools":[{"name":"get_brand_profile","description":"Returns the stored brand asset profile for one databank brand: {state: done, profile} with search salience of brand plus asset words, SERP / AI Overview evidence lines, distinctive brand asset candidates (colour, shape, logo, character, celebrity, tagline, sound, font, pack), AI answer test results (Gemini and OpenAI, not consumers), synthetic panel and Taste Finder link when they exist, competitors, credits and build time. Other states: running {step}, none (never built), error, unknown (brand not in the databank, HTTP 404). Free. Repeat while state is running."},{"name":"build_brand_profile","description":"Builds the asset profile for a databank brand in the background: brand plus asset-word search volumes, stored SERP and AI Overview evidence, LLM extraction of asset candidates tied to evidence numbers, and a repeated AI answer test on Gemini and OpenAI. Returns {state: running} (HTTP 202), or the stored profile when one exists and force is false. Poll get_brand_profile. About 100 Data API credits plus several LLM calls, 1-2 minutes. Only brands listed in the databank are accepted. Visitors who are not signed in can build too (the app caps visitor builds at 5 per IP and 40 in total per hour; over that it answers HTTP 429 {state: busy}). Rebuilding a stored profile with force=true is for signed-in members only."},{"name":"refresh_brand_visuals","description":"Looks up again the logo, person photos and colours of a stored brand asset profile from public sources (Wikidata, Wikimedia Commons, the official site) with one LLM check. Returns {state: running} (HTTP 202), or {state: busy} (HTTP 429; visitors are capped at 20 per IP per hour). Poll get_brand_visuals. Free: no Data API credits, and no Lima is charged."},{"name":"get_brand_visuals","description":"State and result of refresh_brand_visuals for one brand: {state: none|running|done|error, result}. Free. Repeat while state is running."},{"name":"list_profile_jobs","description":"Lists profile builds started since the server last restarted, keyed by market/genre/hash: {state, step, started, ended, cc, g, n, error}. At most 2 builds run at the same time. Free."}],"documentation":"https://daas-brand.listeningmind.ai/llms.txt"},"docs":"https://daas-brand.listeningmind.ai/llms.txt"}