What it does
brandcheck is a small keyless bridge to the hosted AskedThrice measurement service. The service asks buyer questions to OpenAI, Anthropic and Gemini and reports what they answered. A finished measurement gives a verdict in three bands, the number of buyer questions the brand won, the competitors named instead, and which providers answered. There is no 0 to 100 score.
It suits checking whether a brand appears when buyers ask AI assistants for recommendations. The start_visibility_check tool takes brand, website and category, with optional competitors (up to five), location and language (en or es), and returns a runId. The get_visibility_check tool takes that runId and returns status running until the providers finish, so it is polled every 20 to 30 seconds, since a measurement takes about a minute.
No signup or API key is needed. Arguments are forwarded unchanged and upstream results are returned verbatim, including any isError flag. The endpoint and per-request timeout can be overridden through environment variables. A CLI exposes each tool as a subcommand that takes one JSON argument. Failures are reported as askedthrice error, askedthrice error: malformed response, or askedthrice unreachable.
Limitations and requirements
The hosted service allows one measurement per domain every 30 days. This quota is enforced upstream, and a quota_reached answer is passed through unchanged. Requests time out after 60000 ms by default. Optional competitors are limited to five.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
io.github.CloudCorpRecords/brandcheck
Measure whether a brand shows up when buyers ask AI assistants for a recommendation.
v0.1.0As shown on registry.modelcontextprotocol.io when we last read it