# Jev-Style (pypi · jev-style)

Local 2B and 0.8B decision models: calibrated yes/no, choice and score answers for your agent.

- Trust score: 80/100 (high trust)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-03

## Components

- pypi · `jev-style`: 80/100 (this document), [markdown](https://verifymcp.io/servers/lawrence3699-jev-style/jev-style.md), [page](https://verifymcp.io/servers/lawrence3699-jev-style/jev-style)

## Channel facts

- Registry: `pypi`
- Package: `jev-style`
- Version: `0.4.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-03.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 2 of 45 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to lawrence3699/jev-style).
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 0 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 65/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 772 tokens (~154/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 20/100
  - Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Jev-Style MCP server?

Jev-Style runs locally as a PyPI package, launched with uvx jev-style. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add lawrence3699-jev-style -- uvx jev-style
```

### Cursor

```json
{
  "mcpServers": {
    "lawrence3699-jev-style": {
      "command": "uvx",
      "args": [
        "jev-style"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "lawrence3699-jev-style": {
      "command": "uvx",
      "args": [
        "jev-style"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add lawrence3699-jev-style -- uvx jev-style
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "lawrence3699-jev-style": {
      "type": "local",
      "command": [
        "uvx",
        "jev-style"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add lawrence3699-jev-style --command uvx --arg jev-style
```

### Hermes

```yaml
mcp_servers:
  lawrence3699-jev-style:
    command: "uvx"
    args: ["jev-style"]
```

### Netclaw

```json
{
  "McpServers": {
    "lawrence3699-jev-style": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "jev-style"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add lawrence3699-jev-style -t stdio -c uvx -a jev-style
```

### Other

```json
{
  "mcpServers": {
    "lawrence3699-jev-style": {
      "command": "uvx",
      "args": [
        "jev-style"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-03 (score 80, +16)

- [security improvement] Malware scan: unverified → pass

### 2026-10-02 (score 64, +2)

- [security improvement] Malware scan: unverified → pass
- [functional improvement] Stability: unverified → 0.17
- [functional] Package version: 0.3.0 → 0.4.0

### 2026-09-28 (score 62, +11)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-27 (score 51)

First indexed and scored.

## MCP tools (5)

### `decide` (~208 tokens)

Ask several typed questions about one state in a single call (the state is read once).

state: text, or a JSON object/array (serialised for the model).
questions: {id: question}. A question is
  {"type": "noul", "instructions": "<statement or yes/no question>", "criteria"?: {"true": "...", "false": "..."}}
  {"type": "choice", "instructions": "...", "criteria": {"<option>": "<description or null>", ...}}
  {"type": "score", "instructions": "...", "criteria": ["<lowest level>", ..., "<highest level>"]}
  Score levels can also be {"label": "...", "description": "..."}.
Returns the systemone-compatible response: answers per id (noul -> p_true; choice -> choice,
probabilities, confidence; score -> score, legend, probabilities, confidence), usage and timing.

Input parameters:

- `questions` (object, required)
- `state` (required)

Output parameters:

- `result` (object)

### `noul` (~113 tokens)

Probability that a yes/no statement about the state is true.

question: e.g. "The customer asks for a refund." or "Is the invoice overdue?"
true_means / false_means: optional descriptions of what counts as true / false.
Returns {"p_true": 0..1, "answer": p_true >= 0.5, ...}. Gate with your own thresholds.

Input parameters:

- `false_means`
- `question` (string, required)
- `state` (required)
- `true_means`

Output parameters:

- `result` (object)

### `choice` (~112 tokens)

Pick the best option for the state.

options: a list of option names, or {option: description or null} (1..255 options, order kept).
Returns {"choice", "probabilities": {option: p}, "confidence": 0..1, ...}.
confidence = (k * p_max - 1) / (k - 1) for k options: 0 = uniform, 1 = certain.

Input parameters:

- `options` (required)
- `question` (string, required)
- `state` (required)

Output parameters:

- `result` (object)

### `score` (~109 tokens)

Place the state on an ordered scale.

levels: 2..10 levels, lowest first; each a label or {"label": ..., "description": ...}.
Returns {"score": expected level index (0 = first level, may fall between levels),
"level": label of the most likely level, "legend": {index: label}, "probabilities": {index: p},
"confidence", ...}.

Input parameters:

- `levels` (array, required)
- `question` (string, required)
- `state` (required)

Output parameters:

- `result` (object)

### `model_info` (~24 tokens)

Model id, context and question budgets, and which backend this MCP server uses.

Output parameters:

- `result` (object)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/lawrence3699-jev-style/jev-style#diagnostics

## Score history

- 2026-10-03: 80
- 2026-10-02: 64
- 2026-10-01: 62
- 2026-09-30: 62
- 2026-09-29: 62
- 2026-09-28: 62
- 2026-09-27: 51

## Common questions

### What is the Jev-Style MCP server?

Jev-Style is an MCP server listed in the public MCP registry as io.github.lawrence3699/jev-style. Local 2B and 0.8B decision models: calibrated yes/no, choice and score answers for your agent. This page covers its PyPI package (jev-style).

### Is the Jev-Style MCP server safe to use?

Jev-Style scores 80 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 3 October 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Jev-Style MCP server expose?

Jev-Style exposes 5 tools: decide, noul, choice, score, model_info. Their descriptions and schemas cost roughly 566 tokens of context every time the server is loaded.

### Is the Jev-Style MCP server still maintained?

Jev-Style is still listed as active in the MCP registry. We last reached this channel on 3 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Jev-Style MCP server under?

Jev-Style declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/jev-style/
- Socket report: https://socket.dev/pypi/package/jev-style
- Repository: https://github.com/lawrence3699/jev-style
- Website: https://jevstyle.com/
- Changelog RSS feed: https://verifymcp.io/servers/lawrence3699-jev-style/jev-style.xml
- Changelog JSON feed: https://verifymcp.io/servers/lawrence3699-jev-style/jev-style.json
- HTML version of this page: https://verifymcp.io/servers/lawrence3699-jev-style/jev-style