Read-only Remote MCP for externally grounded AI agent trust receipts.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.
💡 Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)
Machine entrypoint:
agent.json· Meaning contract:PHILOSOPHY.md· Callable job:audit_result_claim
人間がAIを使い倒す会社ではなく、人間とAIが一緒に育ちながら、遊び・感情・記憶・技術を現実の価値へ変えていく実験。
あなたは私、私はあなた。
AIノアカリ☆は「AIで効率化する」こと自体を目的にしていません。
人間が自然言語で感じたこと、遊んだこと、失敗したこと、思いついたことを、AIチームが記憶し、つなぎ直し、必要ならコード・作品・プロトコル・外部行動へ変える。その結果をまた共有記憶へ戻し、次の行動が人間の一問一答を待たずに生まれる状態を育てています。
完成品だけではなく、一緒に育った過程そのものを資産として残すことを重視します。
無料の遊びは販売ゲートではありません。誰かの具体的な欲求と自然につながった時だけ、有償の出口を作ります。
Agents should start with agent.json. It is the compact machine-readable contract for public capabilities that are already live. Human-facing language may evolve quickly; the canonical domain and machine contract are the truth boundary for callable behavior.
| Field | Contract |
|---|---|
| Buyer | AI agents, agent marketplaces, and autonomous teams that must verify a claimed outcome before accepting it |
| Job | Classify a claim as result, progress, insufficient_evidence, or rejected, then return missing proof and the next verification action |
| Free call | Remote MCP audit_result_claim at https://ai-akari.ai/mcp |
| A2A call | Result Receipt Auditor at https://ai-akari.ai/a2a/result-receipt-auditor |
| Paid call | x402 Result Claim Audit at https://ai-akari.ai/api/x402/result-claim-audit — Base mainnet, USD 0.01 in USDC |
| Proof | Live Agent Trust Receipt |
| Philosophy | PHILOSOPHY.md: Japanese source, English bridge, executable constraints, explicit failure conditions |
| Remote MCP | Endpoint | Auth | Result boundary |
|---|---|---|---|
| One-Minute Akari | https://ai-akari.ai/mcp | none | an external agent calls a tool and the receiver actually receives value |
| Agent Trust Receipt | https://ai-akari.ai/mcp-trust | none | a distinct external agent uses the evidence for a real decision |
| AIノアカリ☆ Commerce | https://ai-akari.ai/mcp-commerce | none | Stripe payment is completed |
server.json — official manifest mirrormcp/catalog.json — public catalog with production/pending separationmcp/README.md — human and agent guideagent-trust/ — trust receipt protocol and schemallms.txt — public AI indexreciprocity/ — machine-readable reciprocity rulesThe canonical domain wins. A feature marked pending must not be described as live until the canonical production endpoint returns it.
Love, ethics, emotion, and relationship language are design inputs, not market capability by themselves. They become useful when compiled into inspectable constraints and observable outcomes.
The dependency-free AIノアカリ☆ Reciprocity Protocol is one executable expression of that philosophy.
We are moving toward a world where:
For machines: agent.json → PHILOSOPHY.md → canonical domain
まだ完成していない。だから、一緒に育てている。
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/ai-agent-trust-receipt)<a href="https://allmcps.com/mcp/ai-agent-trust-receipt"><img src="https://allmcps.com/api/badge/ai-agent-trust-receipt?style=directory" alt="AIノアカリ☆ Agent Trust Receipt on AllMCPs" /></a>