Agent Receipts MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 46 installs a week from npm. Last commit 17 Jul 2026.
EU AI Act-ready audit trail: signed, tamper-evident receipts proving what your AI agents did.
Today is the operative word: we check Agent Receipts MCP 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 agent-receipts-mcp -- npx -y agent-receipts-mcp
{
"mcpServers": {
"agent-receipts-mcp": {
"args": [
"-y",
"agent-receipts-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.agent-receipts-mcp]
command = "npx"
args = ["-y", "agent-receipts-mcp"]
{
"mcpServers": {
"agent-receipts-mcp": {
"args": [
"-y",
"agent-receipts-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"agent-receipts-mcp": {
"args": [
"-y",
"agent-receipts-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
AGENT_RECEIPTS_DATA (Directory where the receipt vault (SQLite db + signing key) is stored. Defaults to ./data).
The author declared them in the registry entry; get the values from the project itself.
Tamper-evident audit trails for AI agents — Ed25519-signed, hash-chained, EU AI Act ready.
Tamper-evident, Sigstore-signed audit trail for Claude Code agents.
Tamper-proof audit trail for AI agents. Signed receipts, offline-verifiable, zero backend.
Tamper-evident decision audit trail and outcome-weighted memory for AI trading agents.
Policy-gated agent spend with signed receipts and rail-extract audit
Tamper-evident audit trail MCP server for EU AI Act & GDPR compliance.
Tamper-evident record of what your AI agent did, plus local-first verifiable memory.
Auditable memory for AI agents: provable deletion, tamper-evident audit, time-travel recall.
Answers built from our own checks of this server.