API Discovery & Content Evaluation
JEV Evaluate API
Choose preset mode (useCase + input) or custom mode (state + questions); never mix the two. Custom mode supports noul, choice, and score, with independent answers in result.answers. Model, identity, upstream URL, and execution thresholds remain server-owned. Supplied context and questions are sent to TypeSafe. Decisions are advisory; keyword presets judge only supplied business, SERP, candidate, and product-fact evidence. Requires an active Nexscope subscription. Each route or evaluate call deducts 1 Nexscope credit; any selected data API retains its existing billing. Route and evaluate share limits of 20 requests per user per minute, 200 requests globally per minute, and 5,000 requests globally per rolling day; each route or evaluate call counts as one request. Quota admission is sequential: per-user minute, global minute, then global rolling day; an earlier admitted counter remains incremented if a later check rejects the request.
MCP tool name
nexscope_jev_evaluateLegacy MCP endpoint
/api/skill-api/v1/mcpJSON-RPC method
tools/call