Skip to main content
Glama
pZacca

askjev

by pZacca
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

askjev

Unofficial MCP server for Jev, Typesafe AI's System One model. Not affiliated with Typesafe AI.

Give your agent a fast second opinion. It asks a plain question about material it already has, Jev works out whether that is a yes/no, a scale, or a choice, and answers with calibrated probabilities. No generative model in the loop, one round trip, a fraction of the cost and latency of a sub-agent.

Status

Not published yet. The pipeline works end to end against the live API and the router scores 100% on the first evaluation dataset. See docs/EVAL.md.

Related MCP server: jev-mcp

Install

Requires Node 22+ and a Typesafe API key in TYPESAFE_API_KEY.

Claude Code:

claude mcp add askjev -e TYPESAFE_API_KEY=your-key -- npx -y askjev

Claude Desktop, Cursor, and other clients that take a JSON config:

{
  "mcpServers": {
    "askjev": {
      "command": "npx",
      "args": ["-y", "askjev"],
      "env": { "TYPESAFE_API_KEY": "your-key" }
    }
  }
}

On Windows some hosts cannot launch npx directly. Use "command": "cmd" with "args": ["/c", "npx", "-y", "askjev"].

The tool

ask takes the material and a list of questions. Options are only needed when the question has named alternatives.

{
  "state": "Customer writes: charged twice for one order, wants it fixed today.",
  "questions": [
    { "question": "Does the customer ask for a refund?" },
    { "question": "How frustrated is the customer?" },
    { "question": "Which team should handle this?", "options": ["billing", "platform", "mobile"] }
  ]
}

Each answer comes back with probabilities, Jev's confidence, and how the question was routed. Read the confidence before acting on the answer.

Full contract, pipeline diagrams, and the reasoning behind the design: docs/ARCHITECTURE.md. How the router is evaluated: docs/EVAL.md.

Development

npm ci
npm run lint
npm run typecheck
npm test

License

MIT

Available Tools

1 tool
askAsk JevA
Read-only

Ask Jev, a fast non-generative judgment model, one or more questions about some material you already have. Use it for a quick second opinion, a classification, a rating, or a yes/no check instead of reasoning it out yourself or spawning a sub-agent.

Write each question in plain language. Jev decides whether it is a yes/no question, a scale, or a choice:

  • Yes/no: "Does this ticket ask for a refund?" You get the probability of yes.

  • Choice: pass "options" with the named alternatives. "Which team owns this?" with options ["billing", "platform"].

  • Scale: pass "options" as ordered levels, lowest first. "How urgent is this?" with options ["can wait", "this week", "today"]. Without options, a built-in rubric is picked for you:

    • intensity: not at all < slightly < moderately < very < extremely

    • quality: poor < below average < acceptable < good < excellent

    • severity: trivial < minor < moderate < major < critical

    • likelihood: very unlikely < unlikely < uncertain < likely < very likely

    • sentiment: very negative < negative < neutral < positive < very positive

    • frequency: never < rarely < sometimes < often < always

    • agreement: strongly disagree < disagree < neutral < agree < strongly agree

Every answer carries probabilities and Jev's confidence, plus "routing" showing how the question was interpreted. Read the confidence: a low value means the material does not settle the question, so add context or decide another way.

Requires TYPESAFE_API_KEY in the server's environment.

ParametersJSON Schema
NameRequiredDescriptionDefault
stateYesThe material to judge: text, a JSON object, or a JSON array.
questionsYesQuestions about the same state, answered in one round trip.

Output Schema

ParametersJSON Schema
NameRequiredDescription
modelYesThe Jev model that answered.
usageYesToken usage summed over every Jev call made.
answersYesOne entry per question, in input order. A question that could not be answered has kind "error"; the others are still answered.

TDQS

A4.7/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and openWorldHint; the description adds substantial behavioral context: it is non-generative, every answer carries probabilities and confidence, low confidence signals inconclusive material, and routing explains interpretation. It also discloses the TYPESAFE_API_KEY requirement, going well beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but well-structured with clear sections and bullet points. It is front-loaded with the purpose, then dives into usage examples. Every sentence adds value—nothing is filler. It could be slightly more compact, but the detail is justified by the tool's flexibility.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (two parameters, many question types, built-in rubrics) and that an output schema exists (so return format is covered elsewhere), the description is remarkably complete. It explains question interpretation, option semantics, confidence handling, and the API key requirement—nothing an agent needs to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but the description enriches both parameters. It explains how 'state' can be text/JSON, how 'questions' should be phrased, the role of 'options' for choices and scales, and provides built-in rubrics for common scales. This adds meaning far beyond the schema's basic descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a clear verb ('Ask') and resource ('Jev', a fast non-generative judgment model), and defines the exact purpose: answering one or more questions about existing material. It distinguishes itself from reasoning manually or spawning a sub-agent, which is especially useful given no siblings are listed.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says when to use it ('quick second opinion, classification, rating, or yes/no check') and gives a comparison ('instead of reasoning it out yourself or spawning a sub-agent'). It could add explicit 'when not to use' (e.g., for generative tasks), but the guidance is clear and actionable.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

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

  1. 1 tool updatev0.1.0
    • First observedask
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.6/5.0

Scored across 1 tool

Disambiguation5/5

Only one tool exists, so there is no risk of an agent confusing it with any other. The ask tool has a clearly described purpose and modes.

Naming Consistency5/5

With a single tool, there are no naming inconsistencies to evaluate. 'ask' is a simple, clear verb that matches the server's purpose.

Tool Count3/5

One tool is on the thin end of the spectrum, explicitly in the borderline 1-2 range. However, the server's scope is narrow enough that this single tool is functionally sufficient.

Completeness5/5

The ask tool covers yes/no, choice, and scale questions with built-in rubrics and returns confidence and routing, covering the full intended domain. No obvious missing operations for a judgment-query server.

Resources

Related MCP Connectors

Related MCP Servers

  • jev-mcp

    jkudish
    A
    license
    A
    quality
    B
    maintenance
    Enables agents to verify claims against cited evidence, screen content for prompt injection and relevance before reading it, and rank candidates by meaning, all with calibrated probability verdicts.
    3
    45
    MIT

  • jev-mcp

    rashedInt32
    A
    license
    A
    quality
    C
    maintenance
    Enables typed, calibrated judgment calls through classify, score, check, and batched ask tools, each returning full probability distributions for programmatic decisions.
    5
    1
    MIT

  • jev-mcp

    arunav25
    A
    license
    Not graded
    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.
    MIT

  • jev-mcp

    minhgv
    A
    license
    A
    quality
    C
    maintenance
    Provides coding agents and CI with a typed decision layer that sends bounded state and questions to Jev, then returns deterministic actions for review, risk assessment, requirement checks, and verification.
    9
    MIT