Vouchtrail

com.vouchtrailPublished by vouchtrail.comOfficial publisherv1.0.0Updated Oct 24, 2026

Evidence-first trust verdicts for AI-agent services — query one before you transact.

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingSecurity & Monitoring

Overview

AI-generated overview

A remote MCP server that gives an assistant evidence-backed trust verdicts on AI-agent services before you transact with them.

What you can do
Search a directory of reviewed agent services by name or URL, filter by kind and sort results. Retrieve the full verdict and published evidence for a specific service by its numeric id. Get per-dimension scores, a separate confidence figure, an independent-voice count and the underlying evidence for a service before transacting.
When to use it
Useful when an assistant is about to interact with or pay an unfamiliar AI-agent service and you want a quick, sourced trust check rather than a bare rating.
Requirements
Remote endpoint at vouchtrail.com over streamable HTTP; no packages, environment variables or headers declared.
Before you install
Verdicts are third-party assessments, not guarantees; treat scores and confidence as advisory and review the cited evidence yourself before any transaction or payment.

Installation

In SourceWeft

  1. Open Vouchtrail in the dashboard and add it to a workspace.
  2. 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.vouchtrail%2Fvouchtrail/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.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "vouchtrail": {
      "type": "http",
      "url": "https://vouchtrail.com/mcp"
    }
  }
}

Tools

3

get_verdict

Evidence-backed trust verdict for an agent service before you transact. Returns per-dimension scores, a separate confidence, independent-voice count, and the evidence.

Parameterssubjectrequiredmin_evidence_tiermin_reviewer_karmamax_staleness_hoursrequire_human_linked

search_services

Search the directory of reviewed agent services by name/URL, filter by kind, and sort.

Parametersqkindsort

get_service

Full verdict and published evidence for a subject by numeric id.

Parametersidrequired

Version history

1
  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.