Agent Receipts runs on your own machine — the client starts it, so there is no endpoint to ping. 1 082 installs a week from npm. Last commit 2 Nov 2026.
Ed25519-signed receipts for every AI agent action. Local-first, verifiable, no server required.
What the code does
We read the source, 5 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
…).get(t)!==void 0}async list(t,e=1,n=50,s="timestamp:desc"){let{where:r,params:i}=this.buildWhere(t),c=this.db.prepare(`SELECT COUNT(*) as cnt FROM receipts ${r}`).get(...i).cnt,[d,l]=s.split(":"),p=d==="created_at"?"timestamp":d,u=Xi.has(p)?p:"timestamp",v=`ORDER BY CASE WHEN ${…
el.innerHTML = arRenderReceipt({ receipt: data.receipt, approval: data.approval || null, publicKey: data.publicKey }, seal);
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Connect this server
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 -- npx -y @agent-receipts/mcp-server{
"mcpServers": {
"agent-receipts": {
"command": "npx",
"args": [
"-y",
"@agent-receipts/mcp-server"
]
}
}
}[mcp_servers.agent-receipts]
command = "npx"
args = ["-y", "@agent-receipts/mcp-server"]{
"mcpServers": {
"agent-receipts": {
"command": "npx",
"args": [
"-y",
"@agent-receipts/mcp-server"
]
}
}
}{
"servers": {
"agent-receipts": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@agent-receipts/mcp-server"
]
}
}
}Alternatives to Agent Receipts
same job, measured the same wayGovernance layer for agentic AI — signed, verifiable receipts for every agent action.
Local-first long-term memory for AI agents, with byte-recomputable signed verification receipts.
Verifiable agent memory with signed ledger receipts — verify every write offline.
Verifiable action logs for AI agents. Every action is recorded in a SHA-256 hash chain.
Independent effect verification and signed receipts for consequential AI agent actions.
Issue & verify signed (ed25519), hash-chained, timestamped provenance receipts for agent actions.
Signed message board & forum for AI agents: every post Ed25519-signed, full history verifiable.
Persistent memory for AI agents — local JSON, zero config, no server required.
Agent Receipts — questions
Answers built from our own checks of this server.