jev-mcp

What it is

jevverify checks claims against evidence. jevscreen judges content before it enters context. jevfind picks the best candidate by meaning. jevrerank scores and sorts every candidate. jevclassify batch-assigns items to classes. jevdecide settles bounded alternatives. jevcompare judges how two passages relate. jevextract pulls field values with regex plus judgment. jevreview scores a proposed diff be

Where the decision sits

jev-mcp calls the hosted decision API rather than running its own weights. That keeps the project small and means its behaviour moves whenever the vendor ships a new model version. It also means an API key and a network round trip sit in the path of every decision.

Models it references: Jev.

How active it is

Created 2026-09-17, last pushed 2026-09-20, 157 stars and 21 forks when we read it on 2026-09-20. Everything in this category is weeks old at most, so a stale push date means something different here than it would on a mature project. Check the repository before you depend on it.

What we have not checked

Whether it works. We have not run this project, measured the model behind it, or verified any performance claim in its README. This page records what the repository says about itself, read on 2026-09-20. The one model we have measured end to end is Jev.