Postcept runs on your own machine — the client starts it, so there is no endpoint to ping. 43 installs a week from npm. Last commit 22 Jul 2026.
Verify agent actions against the system of record and get signed completion receipts.
Today is the operative word: we check Postcept 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 mcp -- npx -y @postcept/mcp
{
"mcpServers": {
"mcp": {
"args": [
"-y",
"@postcept/mcp"
],
"command": "npx"
}
}
}
[mcp_servers.mcp]
command = "npx"
args = ["-y", "@postcept/mcp"]
{
"mcpServers": {
"mcp": {
"args": [
"-y",
"@postcept/mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"mcp": {
"args": [
"-y",
"@postcept/mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
POSTCEPT_API_KEY (Postcept API key).
The author declared them in the registry entry; get the values from the project itself.
Issue signed receipts for AI agent actions; verify any receipt offline - free, no account.
Exact-action approval for consequential agent actions: request, track, and verify signed receipts.
Independent effect verification and signed receipts for consequential AI agent actions.
Contract-change authorization for AI agents. Signed receipts verify offline.
Issue & verify signed (ed25519), hash-chained, timestamped provenance receipts for agent actions.
Governance layer for agentic AI — signed, verifiable receipts for every agent action.
Append-only, signed, on-chain-verifiable agent action log — record and audit what agents did.
Signed, hash-chained provenance receipts for AI agent actions.
Answers built from our own checks of this server.