ActionProof runs on your own machine — the client starts it, so there is no endpoint to ping. 67 installs a week from npm. Last commit 1 Jul 2026.
Tamper-proof audit trail for AI agents. Signed receipts, offline-verifiable, zero backend.
Today is the operative word: we check ActionProof 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 actionproof -- npx -y actionproof
{
"mcpServers": {
"actionproof": {
"args": [
"-y",
"actionproof"
],
"command": "npx"
}
}
}
[mcp_servers.actionproof]
command = "npx"
args = ["-y", "actionproof"]
{
"mcpServers": {
"actionproof": {
"args": [
"-y",
"actionproof"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"actionproof": {
"args": [
"-y",
"actionproof"
],
"command": "npx"
}
}
}
Contract-change authorization for AI agents. Signed receipts verify offline.
Issue signed receipts for AI agent actions; verify any receipt offline - free, no account.
Governance layer for agentic AI — signed, verifiable receipts for every agent action.
EU AI Act-ready audit trail: signed, tamper-evident receipts proving what your AI agents did.
Verifiable execution for AI agents: Ed25519-signed work contracts and audit trails.
Verifiable agent memory with signed ledger receipts — verify every write offline.
Ed25519-signed receipts for every AI agent action. Local-first, verifiable, no server required.
Tamper-evident audit trails for AI agents — Ed25519-signed, hash-chained, EU AI Act ready.
Answers built from our own checks of this server.