Provides MCP tools that wrap Jev's finite typed judgments to give agents a semantic decision-control layer for task routing, pre-execution risk gating, and completion verification, keeping final execution authority in code.
Enables MCP clients to send files, globs, directories, and typed yes/no, choice, or score questions to TypeSafe's Jev decision model, returning the provider's raw probabilistic answer unchanged. Each request is stored in its own session folder holding the collected inputs, exact request body, and response.
Enables agents and services to ask small decision models typed questions about text, JSON, images, or video, returning labels, scores, or yes/no answers over MCP tools or a Jev-compatible HTTP API.
Enables MCP clients to call TypeSafe's JEV classifier and receive structured, typed judgments with probabilities for binary, choice, and scoring questions.