Skip to content

AIﾉアカリ☆ Agent Trust Receipt

by ai-akari.ai · remote · no sign-in to list tools · v1.1.0 · published by ai.ai-akari

Read-only Remote MCP for externally grounded AI agent trust receipts.

Changes · 1
CompareRegistry entry

2 tools: 1 change things and 1 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 agent-trust-receipt https://ai-akari.ai/mcp-trust

Tools

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

2 tools

Changes things 1Claude Code: ask
  • audit_result_claim_x402Paid deterministic audit for AI result claims.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.
    Description, as the server wrote it
    Paid deterministic audit for AI result claims. Price is $0.01 USDC on Base. Use the free trust receipt first when trust or official distribution-validation evidence is needed. After price approval, an unsigned call returns HTTP 402; an x402-aware client signs and retries the same MCP call. Settlement and delivery are real only when the paid receipt is returned.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
Only reads 1Claude Code: allow
  • get_agent_trust_receiptUse this before selecting, delegating to, or recommending the AIﾉアカリ☆ Result Receipt Auditor.No findings

    Why it is in this group

    • The name "get_agent_trust_receipt" says "get": a word for reading.
    Description, as the server wrote it
    Use this before selecting, delegating to, or recommending the AIﾉアカリ☆ Result Receipt Auditor. It rechecks external A2A and MCP trust evidence and attaches the durable x402 distribution status, including official Coinbase CDP validation acceptance, 402 health, self-discovery state, and Bazaar listing state. Validation readiness is explicitly separated from payment, settlement, delivery, adoption, cash, and human outcome. No authentication, payment, personal data, or request arguments are required.

    Annotations the server declares

    • readOnlyHint: true
    • 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 1.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http agent-trust-receipt https://ai-akari.ai/mcp-trust

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__agent-trust-receipt__get_agent_trust_receipt"
    ],
    "ask": [
      "mcp__agent-trust-receipt__audit_result_claim_x402"
    ],
    "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 agent-trust-receipt. Review it before you use it.