Skip to content

Jev MCP — freepik-company

Go MCP server exposing Jev through OpenRouter or TypeSafe as five tools: decide, classify, verify, rerank and list_models. Each tool call is one paid inference request, answers are validated against the question asked, and the unchanged provider response is returned with its usage cost.

Stars
3
Language
Go
License
APACHE-2.0
Published by
Community
Author
freepik-company
Last verified
Oct 2026

This is one of several Jev listings for the same project. The canonical entry is Jev MCP — jkudish.

About this project

A small, dependency-light MCP server that gives any MCP client typed, probabilistic decisions from Jev, TypeSafe's System One model, through OpenRouter or TypeSafe directly.

Quoted from the project's README. Read the full README.

Highlights

  • Five tools over one call: decide, classify, verify, rerank and list_models, with one paid inference request per tool invocation.
  • Choice, noul and score questions are answered in a single parallel pass, and the model cannot return an option you did not supply.
  • Provider answers are validated against the question sent, so inconsistent or incomplete answers fail the call instead of being repaired.
  • Credentials stay in the server environment, HTTPS is enforced, and a paid call is never retried automatically.

Watch out

Cost scales with how many items and questions you batch into a call rather than with the number of results, since every tool invocation is one billable request. Paid calls are not retried, requests time out at 30 seconds, and inputs and responses are capped at 1 MiB and 2 MiB. Verification is a model judgment over the evidence you supply, not a proof or approval, and no acceptance threshold is imposed on it. Provider error bodies are never surfaced, which hides the detail you would need to debug a rejected key. Independent project, not affiliated with TypeSafe or OpenRouter. Copy reviewed against the repository README on 2026-10-04, not from running it.

Questions about this entry

Short answers drawn from the linked project or page.

More Jev resources like this

16GitHub stars
Shell wrapper that intercepts unknown subcommands, reads the target CLI help output, and asks Jev which documented subcommand matches the intent behind the typo.
Jev Agents & MCP#community#jevbest#catalog-import
14GitHub stars
Opt-in Hermes plugin that routes each turn to one skill: a wide Jev Choice plus request checks gate a narrow fits round, injecting a single ignorable hint line.
Jev Agents & MCP#community#jevbest#catalog-import
LangChain deepagents middleware that replaces SkillsMiddleware with per-turn judging, loading only the SKILL.md files a turn needs so large catalogs stay out of the prompt.
Jev Agents & MCP#community#jevbest#catalog-import
5GitHub stars
A Claude Code function hook that sends AskUserQuestion dialogs to Jev and draws a probability per option above the dialog, so you still choose while seeing how confident the model is.
Jev Agents & MCP#community#jevbest#catalog-import
6GitHub stars
A per-prompt capability router for coding agents: a local BM25 shortlist of installed skills, MCP servers, subagents and commands, then one Jev request injects at most one suggestion plus two runner-ups.
Jev Agents & MCP#community#jevbest#catalog-import
3GitHub stars
An MCP server with a single evaluate_decision tool that returns noul, choice or score probabilities over a diff, log or plan, with output tokens set to zero on every call.
Jev Agents & MCP#community#jevbest#catalog-import
Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai