protogrid

Search / com.bonissystems/trustai-verify

TrustAI Verification

R0· no sign-in

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

v1.0.0 · active · website · descriptor JSON · versions

An agent can connect right now, no human step.Remote endpoint, no authentication, reachable on the last probe.
Quality88good
Trust75of 100
Uptime, 30 days97%
Latency p50298 ms

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "trustai-verify": {
      "type": "http",
      "url": "https://trustailaw.com/api/mcp"
    }
  }
}
claude mcp add --transport http trustai-verify https://trustailaw.com/api/mcp
[mcp_servers.trustai-verify]
url = "https://trustailaw.com/api/mcp"
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "trustai-verify": {
      "type": "remote",
      "url": "https://trustailaw.com/api/mcp",
      "enabled": true
    }
  }
}
{
  "mcpServers": {
    "trustai-verify": {
      "type": "http",
      "url": "https://trustailaw.com/api/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=trustai-verify&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vdHJ1c3RhaWxhdy5jb20vYXBpL21jcCJ9"
}
{
  "servers": {
    "trustai-verify": {
      "type": "http",
      "url": "https://trustailaw.com/api/mcp"
    }
  }
}
{
  "mcpServers": {
    "trustai-verify": {
      "httpUrl": "https://trustailaw.com/api/mcp"
    }
  }
}
extensions:
  "trustai-verify":
    enabled: true
    name: "trustai-verify"
    type: streamable_http
    uri: "https://trustailaw.com/api/mcp"
    timeout: 300

Quality 88 / 100good

protocol75 · weight 25
  • warn
    protocol.modernnewest supported version is 2025-03-26; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
  • n/a
    protocol.statelessonly applies to 2026-07-28 servers
  • pass
    protocol.transportstreamable HTTP
  • n/a
    protocol.list_ttlonly applies to 2026-07-28 servers
authorizationn/a · weight 15
  • n/a
    auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
  • n/a
    auth.secret_in_urlno templated URL
tool hygiene93 · weight 30
  • pass
    tools.descriptionsevery tool has a description
  • warn
    tools.description_length1 tools have descriptions over 1,024 characters, which crowds the context
  • pass
    tools.schemasevery tool has an object input schema
  • pass
    tools.annotations4 of 4 tools declare readOnlyHint or destructiveHint
  • pass
    tools.directory_hintsevery tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
  • pass
    tools.token_costabout 737 tokens to load every tool
  • pass
    tools.api_dumptools are not a one-to-one API dump
stability100 · weight 15
  • pass
    stability.changes5 tool changes in 30 days
  • pass
    stability.rug_pullno tool changed its meaning under the same name
dependenciesn/a · weight 15
  • n/a
    deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

4 tools, about 737 tokens to load them all · tool set 2e2d6d495fb1 · tools last changed 2026-10-15 · checked 2026-10-20 18:06 UTC

Tool changes

  • review_legal_textchangeddescription
    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 · 58% of words in common

    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.)

  • review_legal_textchangedtitle, annotations
  • get_healthchangedtitle, annotations
  • list_checkschangedtitle, annotations
  • get_descriptorchangedtitle, annotations

Full history: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 75 / 100

no-repository
provenance55
liveness99
freshness65
hygiene80

+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. How it is computed.

Endpoints

remoteauthreachableuptime 30dp50protocollast ok
https://trustailaw.com/api/mcp streamable-httpnoneyes97%298 ms2025-03-262026-10-20

Tools (4)

get_descriptorread-onlyReturn 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_healthread-onlyReturn 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_checksread-onlyReturn the structural checks this server performs on legal-AI output, and — explicitly — what it never claims. Information, not legal advice.
review_legal_textread-onlyIndependently 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.)

Schemas: list_tools.

Similar MCP servers

More from com.bonissystems

And 1 more from this publisher.

Official server.json
{
  "name": "com.bonissystems/trustai-verify",
  "title": "TrustAI Verification",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://trustailaw.com/api/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "1.0.0",
  "websiteUrl": "https://trustailaw.com/verify",
  "description": "Neutral referee for legal-AI output: flags orphan quotes and uncited claims. Not legal advice."
}