[ Built with Jev · SDKs and integrations ]
Jev MCP server for agent harnesses
A proof-of-concept MCP server that adds Jev to an existing agent setup.
By Joey Kudish (@jkudish) ·
Built a proof of concept MCP for @typesafeai 's new jev model Use it inside your existing agent harness to verify claims against evidence, screen content before it enters context, and rank candidates by meaning. github.com/jkudish/jev-mcp
238likes on X
How it uses Jev
Agents call it to check claims against evidence, screen content before it enters their context and rank candidates by meaning.
Summary written by JevHub. Figures are the author's own; we haven't reproduced them. The project belongs to its author.
More builds
introducing JevForm, a form that dynamically branches and chooses what to ask next usinng @typesafeai’s Jev in my life i’ve made hundreds of forms with crazy if/then logic. Jev solves it. built with @vercel json-render (by @ctatedev), so theoretically it can support any
26likes on X
I just built Easy-Jev, a Jev demo anyone can try right now! Change the inputs and watch the classifications change in real time. I did my master's thesis on classification models so it's fun to see a modernized version of a very useful alg Typesafe are correct in that LLMs are
87likes on X
I wanted an easier way to test my jev requests and see if my results are improving, so I built jevals! It's a local workbench for testng the Noul, Choice, and Score primitives. You can mix requests as well. You can run a seed command to see and play with some of the examples in
15likes on X