Skip to main content
Glama

Jevx MCP

Run Jev AI typed decisions from any MCP client — Claude, Cursor, Cline, Codex. Give it a state and the questions you branch on, get back a choice, a score or a yes/no, with a calibrated probability on every option.

Jev AI is a zero-shot decision model from TypeSafe: text or JSON in, typed values out — no dataset, fine-tune or retrain when the label set changes. Jevx is an independent playground and API for Jev AI and is not affiliated with TypeSafe AI.

Tools

Tool

What it does

decide

Send a state and up to 16 typed questions, get back choices, scores and noul values with probabilities

validate_questions

Check a question's shape locally, free and without an API key, before spending credits on a malformed request

open_in_jevx

The URL to try or continue a decision in the browser playground

Related MCP server: jevcore-mcp

Install

npx jevx-mcp

Claude Desktop / Claude Code

{
  "mcpServers": {
    "jevx": {
      "command": "npx",
      "args": ["-y", "jevx-mcp"],
      "env": { "JEVX_API_KEY": "sk-..." }
    }
  }
}

Create a key at jevx.org/settings/apikeys. There is no anonymous decisions endpoint — a key is required, same as running the playground signed out.

Cursor / Cline

Point the client at npx -y jevx-mcp (stdio transport) and set JEVX_API_KEY in its environment.

Question shapes

type

criteria

returns

choice

object of option to meaning, two or more options

choice, probabilities, confidence

score

ordered array, low to high

score, probabilities, confidence

noul

exactly the keys true and false

value between 0 and 1, where exactly 0.5 means the model declined

The API answers HTTP 200 with a non-zero code on a refusal (bad key, malformed request); decide and validate_questions both surface that as a normal tool error, not a silent success.

License

MIT

Available Tools

3 tools
decideRun a Jev AI decisionA

Send a state (text or JSON) and up to 16 typed questions to Jev AI on jevx.org, and get back the choice, score or yes/no for each — with a calibrated probability on every option. Needs JEVX_API_KEY. Branch your own code on the returned probabilities, not just the top label; a noul of exactly 0.5 means the model declined to answer.

Inputs: state (required), questions (required), model.

open_in_jevxOpen the Jevx playgroundC

The URL to try or continue a decision in the browser playground.

Inputs: no named parameters.

validate_questionsCheck a Jev AI question shapeA

Run the same shape checks the Jev API enforces, without spending credits or needing an API key. Use this first when writing questions by hand — a malformed question otherwise comes back as a deeply nested validation error.

Inputs: questions (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.5/5.0

    Scored across 3 tools

    Disambiguation5/5

    Each tool has a distinct role: validate_questions is a pre-flight shape check, decide is the core inference call, and open_in_jevx is a browser handoff utility. There is no meaningful overlap or chance of selecting the wrong tool for a given task.

    Naming Consistency3/5

    All names are lowercase snake_case, but the patterns vary: validate_questions is verb_noun, decide is a bare verb, and open_in_jevx is a verb phrase with a product name. The names are readable and intuitive, yet they do not follow a single predictable convention.

    Tool Count5/5

    At three tools, the server is tightly scoped to the Jev decision workflow: validate, run, and hand off to the playground. Every tool earns its place and the small count is appropriate for such a narrow API.

    Completeness4/5

    The core validate-decide-open flow is fully covered with no dead ends for typical usage. Minor gaps exist around decision management or account/credit introspection, but they are not required for the server's stated purpose.

    Maintenance

    ActivitySlowing
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      C
      maintenance
      Enables MCP clients to call TypeSafe's JEV classifier and receive structured, typed judgments with probabilities for binary, choice, and scoring questions.
      1
      8
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables MCP hosts to query Jev's typed decision model—yes/no, choice, and score—with calibrated probabilities, while defaulting to an offline mock and disclosing all egress unless explicitly enabled.
      107
      Apache 2.0
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables MCP clients to get machine-readable yes/no, choice, and score decisions from TypeSafe Jev, bridging fast classification to Cursor and other clients.
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables MCP hosts to send a context, question, and named choices to Jev System One, returning the selected choice, confidence, and per-choice probabilities.
      MIT