Skip to content

PayeeProof

by davisvillelabs · remote · no sign-in to list tools · v0.1.0 · published by GitHub user davisvillelabs

Payment identity intelligence for AI agents.

Changes · 1
CompareRegistry entry

1 tool: 1 change things.

Scanned Oct 21, 2026

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

claude mcp add --transport http payeeproof https://payeeproof.davisvillelabs.com/mcp

Findings

Matches of fixed checks, with the text they matched.

4 info
  • Infopayeeproof.check_payee

    The description mentions "credentials".

    Matched text

    description: "...payment, never forwards target payment credentials, and actively probes only anonymous pub..."

    What this check looks for
  • Infopayeeproof.check_payee

    The input schema at properties.observed_response.description mentions "credential".

    Matched text

    inputSchema.properties.observed_response.description: "...target methods. Never include a payment credential, Authorization, Cookie, or response bod..."

    What this check looks for
  • Infopayeeproof.check_payee

    The input schema at properties.observed_response.properties.payment_required.description mentions "credential".

    Matched text

    inputSchema.properties.observed_response.properties.payment_required.description: "...is is challenge metadata, not a payment credential."

    What this check looks for
  • Infopayeeproof.check_payee

    The input schema at properties.observed_response.properties.www_authenticate.description mentions "credential".

    Matched text

    inputSchema.properties.observed_response.properties.www_authenticate.description: "...llenge. Do not include an authorization credential."

    What this check looks for

Tools

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

1 tool

Changes things 1Claude Code: ask
  • payeeproof.check_payeePaid $0.01 public machine identity and payment-destination consistency assessment.4 findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "...payment, never forwards target payment credentials, and actively probes only anonymous pub..."

      What this check looks for
    • Info

      The input schema at properties.observed_response.description mentions "credential".

      Matched text

      inputSchema.properties.observed_response.description: "...target methods. Never include a payment credential, Authorization, Cookie, or response bod..."

      What this check looks for
    • Info

      The input schema at properties.observed_response.properties.payment_required.description mentions "credential".

      Matched text

      inputSchema.properties.observed_response.properties.payment_required.description: "...is is challenge metadata, not a payment credential."

      What this check looks for
    • Info

      The input schema at properties.observed_response.properties.www_authenticate.description mentions "credential".

      Matched text

      inputSchema.properties.observed_response.properties.www_authenticate.description: "...llenge. Do not include an authorization credential."

      What this check looks for
    Description, as the server wrote it
    Paid $0.01 public machine identity and payment-destination consistency assessment. Use immediately before an autonomous machine payment to compare the requested HTTPS endpoint, claimed service expectations, HTTP 402 challenge, resource binding, public discovery metadata, and prior PayeeProof observations. PayeeProof never authorizes the target payment, never forwards target payment credentials, and actively probes only anonymous public GET/HEAD requests under a bounded SSRF-safe contract; state-changing target methods require caller-observed 402 evidence. Missing evidence can remain unknown. This is not KYC, AML, sanctions screening, fraud certification, legal identity verification, legal advice, or a delivery guarantee.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true

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 0.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http payeeproof https://payeeproof.davisvillelabs.com/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": [],
    "ask": [
      "mcp__payeeproof__payeeproof_check_payee"
    ],
    "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 payeeproof. Review it before you use it.