# ZTL Judge

> Zero-trust logic judge: your AI writes a claim as a ZFL table, the ZTL core judges it.

- name: io.github.inventor1975/ztl-judge
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 97/100
- quality: 83/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.inventor1975%2Fztl-judge
- tools: https://api.protogrid.dev/v1/servers/io.github.inventor1975%2Fztl-judge/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "ztl-judge": {
      "type": "http",
      "url": "https://api.vitalyreznik.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 100
- freshness: 100
- provenance: 90
- drivers: +repository +namespace-matches-repo +website +reachable +uptime-100% +updated-22d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 83/100 (good)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: language (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); examples (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); judge (readOnlyHint, destructiveHint, idempotentHint, openWorldHint)
- pass `tools.token_cost`: about 343 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: 1 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 3, about 343 tokens to load them all
- tool set hash: dd20929251fa2603d67e4497f18f6833
- tools last changed: 2026-09-29T14:45:32.350Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.inventor1975/ztl-judge.svg)](https://protogrid.dev/servers/io.github.inventor1975/ztl-judge)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-09-29 `judge` changed (description)
  - before: Judge a ZFL document with ZTL, a two-valued zero-trust logic. Args: document: The ZFL document, as an object or as JSON text: {"rows": [{"name": ..., "means": ..., "status": ..., "ground": ...}], "claim": ...}. Returns: The verdict (T or F) with its disposition and grade, the receipt, the instruments that applied, the issues found, and what the core read.
  - after: Judge a ZFL document with ZTL, a zero-trust logic: three values, two-valued connectives. Args: document: The ZFL document, as an object or as JSON text: {"rows": [{"name": ..., "means": ..., "status": ..., "ground": ...}], "claim": ...}. Returns: The verdict with its disposition and grade, the receipt, the instruments that applied, the issues found, and what the core read. Read the verdict WITH its disposition: T EARNED = established; F REFUTED = false; F OPEN or Z OPEN = NOT ESTABLISHED, it could still turn either way (do not report it as false) — `why` and `unverified` say what to check; ON CREDIT = holds only on an unverified ground. A compound claim gets T or F; a claim that is a single name gets that name's own value, Z while unverified. The full report is returned whatever `ask` says.

Full history: https://api.protogrid.dev/v1/servers/io.github.inventor1975%2Fztl-judge/changes

## Remotes

- https://api.vitalyreznik.com/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (3)

- `examples`: Worked examples: questions already written as ZFL documents, ready to judge.
- `judge`: Judge a ZFL document with ZTL, a zero-trust logic: three values, two-valued connectives.

    Args:
        document: The ZFL document, as an object or as JSON text:
            {"rows": [{"name": ..., "means": ..., "status": ..., "ground": ...}], "claim": ...}.

    Returns:
        The verdict with its disposition and grade, the receipt, the
        instruments that applied, the issues found, and what the core read.
        Read the verdict WITH its disposition: T EARNED = established; F REFUTED = false; F OPEN or Z OPEN = NOT ESTABLISHED, it could still turn either way (do not report it as false) — `why` and `unverified` say what to check; ON CREDIT = holds only on an unverified ground. A compound claim gets T or F; a claim that is a single name gets that name's own value, Z while unverified.
        The full report is returned whatever `ask` says.
    
- `language`: The ZFL language: the columns of a row, the document fields, their meaning and rules.