Skip to content

TrustAI Verification

by bonissystems.com · remote · no sign-in to list tools · v1.0.0 · published by com.bonissystems

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

Changes · 1
CompareRegistry entry

4 tools: 1 change things and 3 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http trustai-verify https://trustailaw.com/api/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

4 tools

Changes things 1Claude Code: ask
  • review_legal_textIndependently 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 senten…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.)

    Annotations the server declares

    • title: Review legal text for unsupported quotes and claims
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 3Claude Code: allow
  • get_descriptorReturn 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 p…No findings

    Why it is in this group

    • The name "get_descriptor" says "get": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: About this server
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_healthReturn server health: process uptime and a deterministic engine self-check (the structural detectors run on a fixed sample and return the expected flag counts).No findings

    Why it is in this group

    • The name "get_health" says "get": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Server health
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_checksReturn the structural checks this server performs on legal-AI output, and — explicitly — what it never claims.No findings

    Why it is in this group

    • The name "list_checks" says "list": a word for reading.
    Description, as the server wrote it
    Return the structural checks this server performs on legal-AI output, and — explicitly — what it never claims. Information, not legal advice.

    Annotations the server declares

    • title: What it checks, and never claims
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http trustai-verify https://trustailaw.com/api/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__trustai-verify__get_descriptor",
      "mcp__trustai-verify__list_checks",
      "mcp__trustai-verify__get_health"
    ],
    "ask": [
      "mcp__trustai-verify__review_legal_text"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as trustai-verify. Review it before you use it.