Critique a company’s brand from its public website and an optional public document. Sigil returns positioning, visual identity, voice, a brand score, prioritized changes, and a link to the full Read; it does not design logos, generate brand books, or access private company systems.
The last two health checks of this connector failed. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
Scored across 2 tools
start_read initiates a brand critique and returns an id, while check_read retrieves the status or result of that specific read. Their purposes are clearly distinct and complementary, with no overlap.
Both tools follow the same verb_noun pattern (start_read, check_read) using snake_case consistently. The noun 'read' is used uniformly, making the naming predictable.
The server provides only two tools, which is thin for general MCP servers but arguably sufficient for a single-purpose asynchronous service. The 1-2 tool range is borderline per the rubric, earning a middle score.
The tools cover the core async workflow: start a read and check its status/result. Minor gaps exist (e.g., listing past reads or cancelling), but these are not essential for the primary use case.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
check_readstart_read
Add one secure layer between your agents and this server.