TikTok Account Audit

Diagnose a public TikTok account from traceable public evidence without treating inaccessible or missing data as zero.

Compatible MCP routing

• Use one active connection that exposes the compatible KOLSprite semantic tool contract; prefer the SellerSpace Yunya unified MCP when available and authenticated.
• Support direct business tools plus current and legacy Yunya facade entrypoints.
• In direct mode, resolve each required enrichment tool by its semantic business name.
• In Yunya facade mode, when an enrichment tool is not visible at the host's top level, make at most one host-level discovery attempt and prefer the product-specific yunya_search_kolsprite_tools. Query the smallest required enrichment set; use the exact internal tool names and complete input schemas returned, then invoke them through call_read_tool.
• If the product-specific entrypoint is unavailable but the legacy generic yunya__search_tools is discoverable, use it with provider kolsprite, operation read, and the same query. Do not prefer the generic entrypoint when the product-specific one is available.
• Do not guess a facade namespace, internal tool name, wrapper, or arguments. Reuse discovered names, schemas, and evidence for the run.
• A host-level miss for an enrichment tool is not proof of internal absence. Only mark the business tool missing after direct exposure and the available current or legacy facade lookup fail. If neither facade entrypoint can be discovered, report a connector-discovery failure and continue only with the explicitly bounded public-evidence path below, not an unrelated substitute.
• A standalone KOLSprite MCP remains compatible only when the required tool names, input schemas, and response shapes match.
• If both connections are enabled, keep all MCP enrichment on Yunya for the run and never duplicate a paid call across services.
• Treat a missing or incompatible enrichment tool as an evidence gap; preserve the public-evidence fallback below.

Required references