# Jev MCP Server (pypi · jev-mcp-server)

MCP server for Jev (TypeSafe System One): typed decisions with calibrated probabilities.

- Trust score: 57/100 (low)
- Change this week: +7
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-18

## Components

- pypi · `jev-mcp-server`: 57/100 (this document), [markdown](https://verifymcp.io/servers/wangkuangkuang-jev-mcp-server/jev-mcp-server.md), [page](https://verifymcp.io/servers/wangkuangkuang-jev-mcp-server/jev-mcp-server)

## Channel facts

- Registry: `pypi`
- Package: `jev-mcp-server`
- Version: `0.2.2`
- 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 2026-10-18.

- **Supply Chain Security**: 50/100
  - Malware scan not yet available for this package.
  - 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.
  - 0 of 28 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 19/100
  - Repository check failed: no source repository is declared.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 25 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 57/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1326 tokens (~189/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 87/100
  - Stability observed for 26 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 7 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Jev MCP Server server?

Jev MCP Server runs locally as a PyPI package, launched with uvx jev-mcp-server. 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 wangkuangkuang-jev-mcp-server -- uvx jev-mcp-server
```

### Cursor

```json
{
  "mcpServers": {
    "wangkuangkuang-jev-mcp-server": {
      "command": "uvx",
      "args": [
        "jev-mcp-server"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "wangkuangkuang-jev-mcp-server": {
      "command": "uvx",
      "args": [
        "jev-mcp-server"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add wangkuangkuang-jev-mcp-server -- uvx jev-mcp-server
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add wangkuangkuang-jev-mcp-server --command uvx --arg jev-mcp-server
```

### Hermes

```yaml
mcp_servers:
  wangkuangkuang-jev-mcp-server:
    command: "uvx"
    args: ["jev-mcp-server"]
```

### Netclaw

```json
{
  "McpServers": {
    "wangkuangkuang-jev-mcp-server": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "jev-mcp-server"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add wangkuangkuang-jev-mcp-server -t stdio -c uvx -a jev-mcp-server
```

### Other

```json
{
  "mcpServers": {
    "wangkuangkuang-jev-mcp-server": {
      "command": "uvx",
      "args": [
        "jev-mcp-server"
      ]
    }
  }
}
```

## 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.

### 2026-10-18 (score 57, +1)

No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-15 (score 56, +37)

- [security improvement] Injection markers: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Stability: unverified → 0.77
- [functional improvement] MCP protocol: unverified → pass

### 2026-10-13 (score 19, −15)

- [security regression] Malware scan: pass → unverified

### 2026-10-12 (score 34, −16)

- [security regression] Tool safety: pass → unverified
- [security regression] Stability: 0.40 → unverified
- [security improvement] Malware scan: unverified → pass
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Capabilities: pass → unverified
- [functional] First check of Schema quality: unverified

### 2026-10-03 (score 50, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-30 (score 49, +4)

- [functional improvement] Stability: unverified → 0.27

### 2026-09-29 (score 45, 0)

- [security regression] Provenance: unverified → fail

### 2026-09-28 (score 45, −15)

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

## MCP tools (7)

### `choice` (~206 tokens)

Ask Jev (TypeSafe System One) to pick ONE of 2-100 mutually exclusive options, with calibrated probabilities.

The official `choice` question type — for fast, cheap structured decisions:
triage, routing, classification, prioritization, tie-breaking among enumerated
candidates. Returns probabilities over ALL options (not just the winner), so
near-ties are visible. NOT for open-ended generation or multi-step reasoning —
use an LLM for those.

Args:
    question: The decision, e.g. "Which error class is most likely the root cause?"
    options: Mapping of short unique id -> one-line description. 2-100 options.
    context: Optional background facts that inform the decision. Keep it short.

Returns:
    JSON string: {choice, confidence, probabilities (sorted desc), runner_up,
                  model, latency_ms, usage}

Input parameters:

- `context` (string)
- `options` (object, required)
- `question` (string, required)

Output parameters:

- `result` (string)

### `score` (~203 tokens)

Ask Jev (TypeSafe System One) to grade something on an ORDERED scale of 2-8 levels.

The official `score` question type — risk/severity/quality rubrics, e.g.
levels ["minor", "moderate", "severe", "critical"]. Returns a fractional
0-based index into `levels` (1.88 = between levels[1] and levels[2], leaning
to levels[2]), plus confidence and per-level probabilities.

Args:
    question: What to grade, e.g. "Regression risk of renaming public config key X".
    levels: 2-8 unique ordered scale points, low to high.
    context: Optional background facts. Keep it short.

Returns:
    JSON string: {score, nearest_level, confidence, probabilities (sorted desc),
                  model, latency_ms, usage}

Input parameters:

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

Output parameters:

- `result` (string)

### `noul` (~166 tokens)

Ask Jev (TypeSafe System One) a yes/no question; returns a 0-1 degree (>= 0.5 leans yes).

The official `noul` question type — fast, cheap binary checks: "is this change
breaking?", "does this log line match the reported symptom?". No probability
list, just the degree. NOT for questions that need multi-step reasoning — use
an LLM for those.

Args:
    question: A yes/no question, e.g. "Is renaming a public config key a breaking change?"
    context: Optional background facts. Keep it short.

Returns:
    JSON string: {noul, verdict, model, latency_ms, usage}

Input parameters:

- `context` (string)
- `question` (string, required)

Output parameters:

- `result` (string)

### `compare` (~207 tokens)

Ask Jev (TypeSafe System One) which of two candidates — a or b — better satisfies the question.

The official `choice` type as a focused A/B judgment: "which error message is
clearer?", "which rollout plan fits this service better?", "title A or B?".
Returns the preferred side PLUS the probability split, so a 52/48 coin flip
is visible instead of hidden.

Args:
    question: What to judge, phrased so one side can win, e.g. "Which error message is clearer?"
    a: Candidate A text.
    b: Candidate B text.
    context: Optional background facts. Keep it short.

Returns:
    JSON string: {preferred: "a"|"b", confidence, probabilities: {a, b},
                  runner_up, model, latency_ms, usage}

Input parameters:

- `a` (string, required)
- `b` (string, required)
- `context` (string)
- `question` (string, required)

Output parameters:

- `result` (string)

### `verify` (~180 tokens)

Check ONE claim against supplied evidence; returns a 0-1 support degree (>= 0.5 leans supported).

The official `noul` type framed as claim-vs-evidence: fact-check a report
line against its source, confirm a log excerpt actually shows the reported
symptom, validate a summary against the document it summarizes. Evidence is
passed as context — Jev judges only what it is given, never invents evidence.

Args:
    claim: A single falsifiable claim, e.g. "The 404s come from edhub, not the gateway".
    evidence: The evidence text to check the claim against (log excerpt, doc paragraph, diff).

Returns:
    JSON string: {noul, verdict, model, latency_ms, usage}

Input parameters:

- `claim` (string, required)
- `evidence` (string, required)

Output parameters:

- `result` (string)

### `classify` (~213 tokens)

Batch-classify up to 100 items against ONE shared set of categories using Jev.

Runs the official `choice` question type once per item and aggregates the
results — routing support tickets, labeling log lines, triaging inbox items
against your own label set. Much cheaper and faster than an LLM for
mechanical labeling.

Args:
    items: 1-100 non-empty strings to classify.
    options: Mapping of short unique id -> one-line category description. 2-100 options.
    question: Per-item question; the item itself is appended automatically.
    context: Optional background facts shared by all items.

Returns:
    JSON string: {results: [{item, choice, confidence, probabilities}], summary
                  (counts per choice, sorted desc), model, total_latency_ms,
                  usage: {input_tokens, output_tokens, calls, cached_calls}}

Input parameters:

- `context` (string)
- `items` (array, required)
- `options` (object, required)
- `question` (string)

Output parameters:

- `result` (string)

### `setup` (~151 tokens)

One-time onboarding: verify a TypeSafe API key with a live call, then store it locally.

Use when TYPESAFE_API_KEY is not set in the server environment: pass your key
once (get one at https://console.typesafe.ai/settings/keys). It is verified
against the live API, then saved to ~/.config/jev-mcp/key (permissions 0600)
and never echoed back. An existing TYPESAFE_API_KEY env var always takes
precedence over the stored file.

Args:
    api_key: Your TypeSafe API key (from console.typesafe.ai/settings/keys).

Returns:
    JSON string: {ok, stored_path, verified}

Input parameters:

- `api_key` (string, required)

Output parameters:

- `result` (string)

## Diagnostics

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

## Score history

- 2026-10-18: 57
- 2026-10-17: 56
- 2026-10-16: 56
- 2026-10-15: 56
- 2026-10-14: 19
- 2026-10-13: 19
- 2026-10-12: 34
- 2026-10-04: 50
- 2026-10-03: 50
- 2026-10-02: 49
- 2026-10-01: 49
- 2026-09-30: 49
- 2026-09-29: 45
- 2026-09-28: 45
- 2026-09-27: 60
- 2026-09-26: 60
- 2026-09-25: 60
- 2026-09-24: 60
- 2026-09-23: 60
- 2026-09-22: 60

## Common questions

### What is the Jev MCP Server server?

Jev MCP Server is listed in the public MCP registry as io.github.wangkuangkuang/jev-mcp-server. MCP server for Jev (TypeSafe System One): typed decisions with calibrated probabilities. This page covers its PyPI package (jev-mcp-server).

### Is the Jev MCP Server server safe to use?

Jev MCP Server scores 57 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 18 October 2026. 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 MCP Server server expose?

Jev MCP Server exposes 7 tools: choice, score, noul, compare, verify, and 2 more. Their descriptions and schemas cost roughly 1,326 tokens of context every time the server is loaded.

### Is the Jev MCP Server server still maintained?

Jev MCP Server is still listed as active in the MCP registry. We last reached this channel on 18 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 MCP Server server under?

Jev MCP Server declares the MIT 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-mcp-server/
- Socket report: https://socket.dev/pypi/package/jev-mcp-server
- Changelog RSS feed: https://verifymcp.io/servers/wangkuangkuang-jev-mcp-server/jev-mcp-server.xml
- Changelog JSON feed: https://verifymcp.io/servers/wangkuangkuang-jev-mcp-server/jev-mcp-server.json
- HTML version of this page: https://verifymcp.io/servers/wangkuangkuang-jev-mcp-server/jev-mcp-server