ask10ais

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Independent measurements of how 12 AI models answer brand questions in Chinese and English.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "ask10ais": {
      "url": "https://ask10ais.com/api/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (6)

• find_brand read-only

  Search ask10ais's published measurements (every public ranking and every scenario cell, asked in both Chinese and English) for a brand name. Returns its rank in each ranking and its mention rate with a 95% interval in each scenario, each with a link to the source page. Matching is a case-insensitive substring match plus registered aliases.

  Parameters:

  • query (required) — string — A brand or company name only, e.g. 'PETKIT' or '小佩'. Do not include personal information or conversation text.
  • locale — string — Language for names, reading rules and citation templates: 'en' or 'zh'.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• list_rankings read-only

  List ask10ais's public ranking questions with their latest measurement date, panel size and top brands.

  Parameters:

  • locale — string — Language for names, reading rules and citation templates: 'en' or 'zh'.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_ranking read-only

  Latest measurement of one public ranking: each brand's rank and index score, merged spellings, panel size and completeness, plus a citation template.

  Parameters:

  • topic_id (required) — integer — topic_id from list_rankings or find_brand.
  • limit — integer — How many brands to return (1–50).
  • locale — string — Language for names, reading rules and citation templates: 'en' or 'zh'.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• list_scenario_collections read-only

  List published scenario collections: buying scenarios in one category, each asked with several phrasings and repeats in Chinese and English.

  Parameters:

  • locale — string — Language for names, reading rules and citation templates: 'en' or 'zh'.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_scenario_mention_rates read-only

  Mention rates with 95% Wilson intervals for one scenario in one language: which brands models mention, how often, and how many models mention them.

  Parameters:

  • collection (required) — string — Collection slug from list_scenario_collections.
  • scenario_id (required) — string — Scenario id, e.g. 'S1'.
  • limit — integer — How many brands to return (1–50).
  • locale — string — Which language the scenario was asked in: 'en' or 'zh'. Results differ by language.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• verify_certificate read-only

  Check an ask10ais certificate number (ASK10AIS-YYYY-NNNNNN): whether it exists, what it records, and whether it is valid or voided.

  Parameters:

  • certificate_no (required) — string — e.g. ASK10AIS-2026-000001
  • locale — string — Language for names, reading rules and citation templates: 'en' or 'zh'.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

Publisher website

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.