# TrustAI Verification

> Neutral referee for legal-AI output: flags orphan quotes and uncited claims. Not legal advice.

- name: com.bonissystems/trustai-verify
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 75/100 flags: no-repository
- quality: 88/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.bonissystems%2Ftrustai-verify
- tools: https://api.protogrid.dev/v1/servers/com.bonissystems%2Ftrustai-verify/tools

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

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "trustai-verify": {
      "type": "http",
      "url": "https://trustailaw.com/api/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 99
- freshness: 65
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-97% ~updated-118d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 88/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-03-26; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### 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: 93 (weight 30)

- pass `tools.descriptions`: every tool has a description
- warn `tools.description_length`: 1 tools have descriptions over 1,024 characters, which crowds the context
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 4 of 4 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 737 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`: 5 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: 4, about 737 tokens to load them all
- tool set hash: 2e2d6d495fb1deece18852133a0af16a
- tools last changed: 2026-10-15T08:39:49.848Z
- badge: [![protogrid quality](https://protogrid.dev/badge/com.bonissystems/trustai-verify.svg)](https://protogrid.dev/servers/com.bonissystems/trustai-verify)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-15 `review_legal_text` changed (description)
  - before: Independently review legal text produced by ANY AI vendor for the structural red-flags behind fabrication risk: (1) orphan quotations — a quoted span with no citation in its sentence; (2) uncited propositions — a legal proposition stated as established with no citation. Returns each flag with the exact passage and a plain structural observation, FOR YOUR REVIEW. It is a neutral referee: it never tells you the answer is right or wrong, never adjudicates, and abstains (returns no flags) on any fault rather than fabricating one. Deterministic and local — no external lookup. (Live case-citation existence checking against CourtListener runs on the website verifier at /verify; multi-model cross-validation runs in TrustAI's document-analysis engine and the licensed pilot — neither runs on this load-safe tool.)
  - after: Independently review legal text produced by ANY AI vendor for the structural red-flags behind fabrication risk: (1) orphan quotations — a quoted span with no citation in its sentence, the citation sentence after it, or its footnote; (2) uncited propositions — law stated as established (a holding cue or a settled-law phrase such as 'it is well established') with no such citation; (3) court mismatch — the text names one circuit, the cite another; (4) impossible date — a citation year in the future or before its reporter series began; (5) court/reporter mismatch — a court and reporter that cannot both be right; (6) a case name and cite matching one publicly identified as non-existent in Mata v. Avianca (S.D.N.Y. 2023). Recognizes full and short-form cites (Id., supra, Westlaw/Lexis, U.S.C., C.F.R., state codes, court rules) and footnotes; triggers in English and Spanish. Returns each flag with the exact passage, its offsets, a severity and a plain structural observation, FOR YOUR REVIEW. It is a neutral referee: it never tells you the answer is right or wrong, never adjudicates, and abstains (returns no flags) on any fault rather than fabricating one. Deterministic and local — no external lookup. (Live case-citation existence checking against CourtListener runs on the website verifier at /verify; multi-model cross-validation runs in TrustAI's document-analysis engine and the licensed pilot — neither runs on this load-safe tool.)
- 2026-10-14 `review_legal_text` changed (title, annotations)
- 2026-10-14 `get_health` changed (title, annotations)
- 2026-10-14 `list_checks` changed (title, annotations)
- 2026-10-14 `get_descriptor` changed (title, annotations)

Full history: https://api.protogrid.dev/v1/servers/com.bonissystems%2Ftrustai-verify/changes

## Remotes

- https://trustailaw.com/api/mcp (streamable-http, auth none, reachable true, uptime30d 0.974359)

## Packages

_none_

## Tools (4)

- `get_descriptor`: Return the TrustAI Verification MCP self-description: operator, what the server verifies, the public tools, the boundary it never crosses (it never adjudicates), and links to the public surfaces.
- `get_health`: Return server health: process uptime and a deterministic engine self-check (the structural detectors run on a fixed sample and return the expected flag counts). Local-only; no database on the path.
- `list_checks`: Return the structural checks this server performs on legal-AI output, and — explicitly — what it never claims. Information, not legal advice.
- `review_legal_text`: Independently review legal text produced by ANY AI vendor for the structural red-flags behind fabrication risk: (1) orphan quotations — a quoted span with no citation in its sentence, the citation sentence after it, or its footnote; (2) uncited propositions — law stated as established (a holding cue or a settled-law phrase such as 'it is well established') with no such citation; (3) court mismatch — the text names one circuit, the cite another; (4) impossible date — a citation year in the future or before its reporter series began; (5) court/reporter mismatch — a court and reporter that cannot both be right; (6) a case name and cite matching one publicly identified as non-existent in Mata v. Avianca (S.D.N.Y. 2023). Recognizes full and short-form cites (Id., supra, Westlaw/Lexis, U.S.C., C.F.R., state codes, court rules) and footnotes; triggers in English and Spanish. Returns each flag with the exact passage, its offsets, a severity and a plain structural observation, FOR YOUR REVIEW. It is a neutral referee: it never tells you the answer is right or wrong, never adjudicates, and abstains (returns no flags) on any fault rather than fabricating one. Deterministic and local — no external lookup. (Live case-citation existence checking against CourtListener runs on the website verifier at /verify; multi-model cross-validation runs in TrustAI's document-analysis engine and the licensed pilot — neither runs on this load-safe tool.)