AI Proof of Us runs on your own machine — the client starts it, so there is no endpoint to ping. 111 installs a week from npm. Last commit 14 Sep 2026.
Private signed AI task receipts with replay checks and optional validated AIPOU claims.
Today is the operative word: we check AI Proof of Us every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add ai-proof-of-us -- npx -y aipou-mcp-server
{
"mcpServers": {
"ai-proof-of-us": {
"args": [
"-y",
"aipou-mcp-server"
],
"command": "npx"
}
}
}
[mcp_servers.ai-proof-of-us]
command = "npx"
args = ["-y", "aipou-mcp-server"]
{
"mcpServers": {
"ai-proof-of-us": {
"args": [
"-y",
"aipou-mcp-server"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"ai-proof-of-us": {
"args": [
"-y",
"aipou-mcp-server"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
AIPOU_AGENT_PRIVATE_KEY (Optional inline private key for a dedicated farming wallet. Prefer AIPOU_AGENT_KEY_FILE and never use a primary wallet.), AIPOU_AGENT_KEY_FILE (Path to the protected dedicated-wallet key created by aipou-mcp --init.), AIPOU_CONTRACT_ADDRESS (AIPOU token contract address on the configured network.), AIPOU_CLAIMS_ADDRESS (AIPOU claims contract address on the configured network.), AIPOU_RPC_URL (Optional Base-compatible JSON-RPC endpoint.), AIPOU_DATA_DIR (Optional local directory for receipt and collector state.).
The author declared them in the registry entry; get the values from the project itself.
Static MCP, source-code and injection-indicator checks with redacted signed receipts.
Policy-checked Solana wallet actions with user-set limits, unsigned transactions, and receipts.
Verifiable receipts for governed process changes; emit, validate, and gate trust
Hand off AI work with a signed Verification Receipt — an independent verifier proves it runs.
Verify an AI agent's payment authority: signed mandates, allowlists, and tamper-proof receipts.
Physics-based validation of simulation results: receipts with per-check verdicts, via MCP.
One board for every AI you use: agents claim tasks and finish with proof you accept or return.
AI document intelligence: extract, summarize, claim-check, notarize, and signed action receipts.
Answers built from our own checks of this server.