MODEL CONTEXT PROTOCOL / COMMUNITY CASE
jev-mcp
A judgment toolbox for agents: verification, screening, semantic matching and ranking, classification, and extraction.
Agents routinely need a decision that is not a generation: does this pass, which of these matches, how should this be labelled, what is the fact being asked for.
jev-mcp collects those into a single set of tools reachable over the Model Context Protocol, so any compatible assistant can call them alongside its other tools.
Each tool routes a specific judgment through Jev: verification checks a claim, screening and matching compare candidates against a criterion, classification assigns a label, and extraction pulls one value out of unstructured input.
Case notes by JevCases. Repository snapshot dated ; claims not independently reproduced.
← RETURN TO THE CASE INDEX