"author:devbux" matching MCP servers:

Enables agents to ask TypeSafe AI's Jev decision model typed questions — choices, scores, true/false propositions, and image bounding boxes — about a text or JSON state, returning structured answers with calibrated probabilities and confidence instead of free-form prose. Supports images, multi-question batch calls, and long-context requests over stdio.

Enables MCP clients to obtain typed, probabilistic decisions from text or structured state and up to four images—choosing among labeled options, scoring on ordered scales, and estimating whether propositions are true—for routing, triage, moderation, risk scoring, and similar agent workflows.