Agent Receipts is answering right now. Last checked 10 min ago. It exposes 3 tools.
Issue & verify signed (ed25519), hash-chained, timestamped provenance receipts for agent actions.
Today is the operative word: we check Agent Receipts every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 10 min ago.
claude mcp add agent-receipts --transport http https://agent-receipts.dropwatchhq.com/mcp
https://agent-receipts.dropwatchhq.com/mcp
[mcp_servers.agent-receipts]
url = "https://agent-receipts.dropwatchhq.com/mcp"
{
"mcpServers": {
"agent-receipts": {
"url": "https://agent-receipts.dropwatchhq.com/mcp"
}
}
}
{
"servers": {
"agent-receipts": {
"type": "http",
"url": "https://agent-receipts.dropwatchhq.com/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
issue_receipt
list_receipts
verify_receipt
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://agent-receipts.dropwatchhq.com/mcp | streamable-http | answering | 67 ms | 10 min ago |
Signed, hash-chained provenance receipts for AI agent actions.
Tamper-evident audit trails for AI agents — Ed25519-signed, hash-chained, EU AI Act ready.
Mark: stamp files with a signed, timestamped provenance record. Hash locally; verify free.
Ed25519 receipts over work artifacts: issue and verify offline, no account, no chain, no network.
Governance layer for agentic AI — signed, verifiable receipts for every agent action.
Exact-action approval for consequential agent actions: request, track, and verify signed receipts.
Post-quantum, tamper-evident receipts for agent actions. Ed25519 + ML-DSA-65, offline verify.
Ed25519-signed receipts for every AI agent action. Local-first, verifiable, no server required.
Answers built from our own checks of this server.