Categories › AI & Agents › Thinking, planning & prompt tools
Independent measurements of how 12 AI models answer brand questions in Chinese and English.
Remote server: your requests and data go to ask10ais.com. Claude Code: claude mcp add --transport http ask10ais https://ask10ais.com/api/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
find_brand — Search ask10ais's published measurements (every public ranking and every scenario cell, asked in both Chinese and English) for a brand name.list_rankings — List ask10ais's public ranking questions with their latest measurement date, panel size and top brands.get_ranking — Latest measurement of one public ranking: each brand's rank and index score, merged spellings, panel size and completeness, plus a citation list_scenario_collections — List published scenario collections: buying scenarios in one category, each asked with several phrasings and repeats in Chinese and English.get_scenario_mention_rates — Mention rates with 95% Wilson intervals for one scenario in one language: which brands models mention, how often, and how many models mentioverify_certificate — Check an ask10ais certificate number (ASK10AIS-YYYY-NNNNNN): whether it exists, what it records, and whether it is valid or voided.Not tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.