LLM Audit
Server Details
Measure whether AI assistants actually recommend a brand, from measured answers.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- nahuelsoria/llmaudit-mcp
- GitHub Stars
- 1
- Server Listing
- askedthrice-mcp
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 2 tools
The two tools form a clean async job pair: start_visibility_check initiates a measurement and get_visibility_check polls/retrieves its result. Their descriptions make the polling semantics explicit (20-30s intervals, 'running' status), so there is no risk of misselection.
Both names use the consistent verb_noun pattern (start_/get_ + visibility_check) on the same resource noun. The naming makes the create/poll relationship immediately legible.
Only two tools exist, and one (start_visibility_check) is a deprecation stub that just returns 'closed' and a marketing link, leaving effectively a single working tool. That is far too thin for a usable surface.
The start/get async pattern would be a complete lifecycle, but the entry point is disabled, so an agent cannot initiate any new measurement — a dead end for the primary use case. Only reading previously started measurements remains possible, with no cancel/status-listing or account-scoped alternatives.
Available Tools
2 toolsget_visibility_checkGet visibility checkARead-onlyIdempotentInspect
Collect the result of a measurement started with start_visibility_check. Returns status running while the providers are still answering, so poll every 20 to 30 seconds. When ready it reports a verdict, how many of the buyer questions the brand won, which competitors were named instead, and which providers actually answered.
Inputs: runId (required).
start_visibility_checkStart visibility checkAInspect
Closed: Asked Thrice no longer runs free measurements. Calling it returns status closed and the link to the paid scan at askedthrice.com, which needs an account. Measurements started before the change can still be read with get_visibility_check.
Inputs: brand (required), website (required), category (required), language, +2 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Measure whether AI assistants actually recommend a brand, from measured answers.
Measure whether AI assistants mention your brand. Reports, model answers, scans, free site tools.
Measure how AI assistants cite your brand. Returns measured data and ready-to-apply fixes.
See how often AI answers name and link your brand, which rivals they name and which sites they cite.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables querying how often a brand is recommended by AI search and chat surfaces, returning recommendation and inclusion rates for any given brand.MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to check whether AI assistants recommend a brand and audit a site's AI-agent readiness, providing visibility scores and specific gaps.MIT
- AlicenseAqualityCmaintenanceProvides twelve read-only tools that report how often ChatGPT, Claude, Gemini, Perplexity and Google AI Overviews name and cite a brand, covering visibility, share of voice, sentiment, competitor mentions, sources, alerts and ranked recommendations with the underlying answers. It lets users query these measurements directly from Claude, Cursor or any MCP client, with denominators and null-handling rules included so results are interpreted correctly.1291 npmMIT
- AlicenseAqualityDmaintenanceTrack brand visibility across ChatGPT, Perplexity, Claude, and Gemini.611MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.