ai-audit-trail runs on your own machine — the client starts it, so there is no endpoint to ping. 155 installs a week from pypi. Last commit 10 May 2026.
Tamper-evident audit trails for AI agents — Ed25519-signed, hash-chained, EU AI Act ready.
Today is the operative word: we check ai-audit-trail 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-audit-trail -- uvx ai-audit-trail
{
"mcpServers": {
"ai-audit-trail": {
"args": [
"ai-audit-trail"
],
"command": "uvx"
}
}
}
[mcp_servers.ai-audit-trail]
command = "uvx"
args = ["ai-audit-trail"]
{
"mcpServers": {
"ai-audit-trail": {
"args": [
"ai-audit-trail"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"ai-audit-trail": {
"args": [
"ai-audit-trail"
],
"command": "uvx"
}
}
}
EU AI Act-ready audit trail: signed, tamper-evident receipts proving what your AI agents did.
Tamper-evident, SHA-256 hash-chained audit trail and observability for AI agents.
Tamper-evident, Sigstore-signed audit trail for Claude Code agents.
Signed, hash-chained, tamper-evident AI incident records. EU AI Act Article 73 serious-incident repo
Tamper-evident audit trail MCP server for EU AI Act & GDPR compliance.
Verifiable execution for AI agents: Ed25519-signed work contracts and audit trails.
Issue & verify signed (ed25519), hash-chained, timestamped provenance receipts for agent actions.
Headless browser with SHA-256 audit trails and Ed25519-signed proof bundles for AI agents.
Answers built from our own checks of this server.