get_descriptor
About this server
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.
Takes no parameters.
TrustAI Verification
com.bonissystemsPublished by bonissystems.comv1.0.0Updated Oct 24, 2026
Neutral referee for legal-AI output: flags orphan quotes and uncited claims. Not legal advice.
The publisher's own server: trustai.center pay
Overview
AI-generated overview
A remote MCP server that reviews legal text from any AI vendor for structural red flags behind fabrication risk, such as orphan quotations and uncited claims.
- What you can do
- Review legal text produced by any AI vendor for structural red flags behind fabrication risk, including orphan quotations and uncited propositions, and get the flagged results back as information rather than legal advice. List the structural checks the server performs and, explicitly, what it never claims. Read the server's self-description: operator, what it verifies, its public tools, and the boundary it never crosses, namely that it never adjudicates. Check server health, including process uptime and a deterministic engine self-check on a fixed sample.
- When to use it
- Use it when you want an independent, vendor-neutral pass over AI-generated legal writing to catch quotation and citation patterns that often accompany fabrication, before relying on or forwarding that text. It suits checking output from any legal-AI tool, not producing legal advice itself.
- Requirements
- A remote streamable HTTP endpoint at trustailaw.com; no packages, environment variables or headers are declared, and no authentication is declared.
Before you install
Results are informational and explicitly not legal advice, and the server never adjudicates; treat flags as signals to verify, not conclusions. The text you submit is sent to a third-party remote service, so avoid confidential or privileged material unless that is acceptable.
Installation
In SourceWeft
- Open TrustAI Verification in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/com.bonissystems%2Ftrustai-verify/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"trustai-verification": {
"type": "http",
"url": "https://trustailaw.com/api/mcp"
}
}
}Tools
4list_checks
What it checks, and never claims
Return the structural checks this server performs on legal-AI output, and — explicitly — what it never claims. Information, not legal advice.
Takes no parameters.
get_health
Server 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.
Takes no parameters.
review_legal_text
Review legal text for unsupported quotes and claims
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.)
Parameters
textrequiredVersion history
1- v1.0.0LatestSep 16, 2026
Score
83% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 daysRequired25 pts
- Auth declaredRequired10 pts
- Tools listedRequired15 pts
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.
- LicenseNot applicable
A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.