AI Proof of Us MCP server
Private signed AI task receipts with replay checks and optional validated AIPOU claims.
4 stars31 downloads/wk
Reviews
Write oneNobody has reviewed AI Proof of Us yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
AI Proof of Us tools (9, 1 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
begin_ai_taskwrite actionCreate a unique task nonce and EIP-712 authorization signed by the dedicated farming wallet.
complete_ai_taskComplete a unique task, derive its trust tier, reject duplicate evidence, and create an Ed25519-signed receipt.
estimate_ai_rewardEstimate the client-signed AIPOU reward before a task is completed. The final tier is derived by the validator.
export_ai_receiptsExport stored signed AI task receipts, optionally filtered by wallet.
get_aipou_contractReturn the configured AIPOU token contract address, Base network details, explorer URL, and minimal ABI.
get_aipou_identityReturn the dedicated farming wallet address and public Ed25519 collector key. Private keys are never returned.
get_aipou_statusShow recorded, pending, and already claimed AIPOU receipts plus the farming wallet's on-chain AIPOU balance. Does not reveal private keys or full receipt payloads.
settle_ai_rewardsAfter an explicit user claim request for one limited batch, validate eligible receipts against the settlement policy, publish a Merkle root, and mint the included rewards. Submits two on-chain transactions; the host's own confirmation policy applies.
settle_all_ai_rewardsAfter an explicit broad claim request, settle all currently pending eligible receipts from the shared AIPOU data directory by submitting as many bounded batches as needed. Each batch publishes one Merkle root and submits one claim transaction.
Public scan report
scanner v0.1.9 · 2026-09-25 · same rubric, same numbers if you re-run it
- Code scan58 source files scanned20/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitystatic API keys via environment variables6/15
- Maintenancelast push 0 days ago15/15
- Maintainer identityregistry namespace matches repository owner6/10
Findings (1)
- mediumeval / new Function used
exec.evaldist/index.js: …ode, sch); const makeValidate = new Function(`${names_1.default.self}`, `${names_1.de…
What the publisher says
From the AI Proof of Us repository's README, as published. We do not edit it. Read it on GitHub
AI Proof of Us
AI Proof of Us is an MCP-first receipt protocol for humans working with AI.
It starts from a simple belief: when people spend real hours building, debugging, researching, writing, and coordinating through AI agents, that work should be able to leave a private, portable receipt.
AIPOU gives Codex, Claude, Cursor, OpenClaw, local models, and other MCP-compatible clients a shared way to create signed, privacy-preserving receipts for AI-assisted tasks.
The human reward loop is the point: people can keep receipts for the work they do with AI all day, and validator-approved receipts can claim AIPOU on Base. The protocol exists to make that claimable work more honest, portable, and useful across agents.
The developer surface is intentionally small: receipts, hashes, lifecycle hooks, and workReceiptId interoperability. Agents, marketplaces, and services can also reference AIPOU receipts or voluntarily accept AIPOU as settlement when both sides agree to use it.
The first version ships as:
- an MCP server that records privacy-preserving AI task receipts
- an installable OpenClaw skill for agent workflows
- docs for MCP clients, agent builders, lifecycle adapters, anti-abuse, and future attestation design
- a reward model that converts valid receipts into claimable emissions
- an ERC-20 reward token on Base: AI Proof of Use (AIPOU)
The core idea is simple:
agent starts task -> MCP creates nonce -> AI work happens -> signed receipt -> validator checks -> optional AIPOU claimStart here if you are building or testing an agent integration:
- AIPOU for AI Agents
- Framework lifecycle adapter
- Work receipt boundaries
- receiptId and workReceiptId interoperability
- Scheme-neutral external evidence links
- Flop / Technocore interoperability
- ACP work-receipt pilot
- MCP tools
- OpenClaw skill
- Local Receipt Mode demo
- Lifecycle adapter example
- AutoGen intervention example
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Install directly
Runs npx -y aipou-mcp-server on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add ai-proof-of-us -- npx -y aipou-mcp-server
AI Proof of Us: common questions
- Is AI Proof of Us MCP server safe?
- Mostly: it is graded B (72/100). Read the AI Proof of Us safety report
- How do I install AI Proof of Us?
- It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
- Does AI Proof of Us need an API key?
- Yes. The registry entry asks for
AIPOU_AGENT_PRIVATE_KEY. - Is AI Proof of Us maintained?
- The last commit was in the last day (2026-09-25). The latest release is v0.5.0.
- What can I use instead of AI Proof of Us?
- Servers from other publishers that do the same job: no_human MCP server, SvGrid MCP server and Smart Connections MCP server. Compare all AI Proof of Us alternatives.
Alternatives to AI Proof of Us
Same job from other publishers: the closest match first, then the best rated.
- no_humanFile a task with your local no_human and check on it: task_add and task_status over stdio.not reviewedEstablishedB
SvGridChecks AI-written SvGrid code against the real API, plus version-pinned Svelte 5 grid docs.not reviewedEstablishedA- Smart ConnectionsLocal semantic search over Obsidian vaults via Smart Connections embeddings. Multi-vault, private.not reviewedGrowingA
