Skip to content

Viorant JEV MCP

Viorant's hosted MCP service exposing Jev Noul, Choice and Score decisions to agents, with a free credit tier.

Service

This summary is based on how curated lists describe the project; its README was not available to review.

Overview

Viorant offers hosted Jev decisions through MCP. According to the list summary, it exposes Noul, Choice and ordered Score questions and returns calibrated probabilities that clients can use to route, verify, screen, rank or escalate.

The summary notes that Viorant's free plan includes 2,500 one-time Vio Credits, described as theoretically enough for up to 25 million Jev input tokens if used only for Jev. Implementation and pricing details beyond that are not available here.

What the decision model decides

TypeQuestionAnswers
Yes / noAgent-posed yes/no question(inferred)yes · no
ChoiceAgent-posed choice(inferred)—
ScoreAgent-posed ordered score(inferred)—

How it works

  1. Connect an MCP client to Viorant.
  2. Send state and typed questions.
  3. Receive probabilities and act on them.

Strengths

  • Hosted MCP access without self-hosting.
  • Free starting credits.

Caveats

  • Third-party hosted service.
  • Known only from a list summary.

Getting started

See https://viorant.ai/jev

At a glance

Type
Service
Runtime
hosted MCP service

Use cases and integrations

How curated lists describe it

  • Agent infrastructure: exposes hosted `Noul`, `Choice`, and ordered `Score` decisions through MCP, returning calibrated probabilities that clients can use to route, verify, screen, rank, or escalate; Viorant's Free Plan includes 2,500 one-time Vio Credits, theoretically enough for up to 25 million JEV input tokens when used exclusively for JEV.

    yibie/awesome-jev

Frequently asked questions

What does it provide?

Hosted Noul, Choice and Score decisions over MCP.

Is there a free tier?

Yes, 2,500 one-time credits, per the summary.

Is it from TypeSafe?

No, it is a Viorant service.

Related projects

  • DeepSeek Harness plugin that registers a native jev_decide tool and declares its own policy for when the agent should ask Jev.

    PluginbetaJavaScript
  • Hermes skill that calls Jev as a typed tiebreaker, returning Choice, Score or Noul probabilities so the agent can act or escalate.

    Agent skillbetaPython
  • Portable decision layer for agent harnesses: Jev picks from host-supplied capabilities while the host keeps permissions and execution.

    ProjectbetaTypeScript
  • Rust MCP server for Codex that hands classification, relevance, candidate selection and evaluation to Jev with accept/verify policies.

    MCP serverbetaRust
  • Jev decision layer for agents: seven MCP tools, an embeddable library and escalate-only Claude Code hooks at harness boundaries.

    MCP serverbetaTypeScript
  • Local MCP server that runs versioned packs of typed Jev judgments, with a closed tool catalogue and a key configured once.

    MCP serverbeta