TrustNotch runs on your own machine — the client starts it, so there is no endpoint to ping. 100 installs a week from pypi.
Tamper-evident audit logs for AI agents: submit, fetch, and verify cryptographic proof bundles.
Nothing serious here today
Today is the operative word: we check TrustNotch every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
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 trustnotch-mcp -e 'TRUSTNOTCH_API_KEY=<TRUSTNOTCH_API_KEY>' -- uvx trustnotch-mcp{
"mcpServers": {
"trustnotch-mcp": {
"command": "uvx",
"args": [
"trustnotch-mcp"
],
"env": {
"TRUSTNOTCH_API_KEY": "<TRUSTNOTCH_API_KEY>"
}
}
}
}[mcp_servers.trustnotch-mcp]
command = "uvx"
args = ["trustnotch-mcp"]
env = { TRUSTNOTCH_API_KEY = "<TRUSTNOTCH_API_KEY>" }{
"mcpServers": {
"trustnotch-mcp": {
"command": "uvx",
"args": [
"trustnotch-mcp"
],
"env": {
"TRUSTNOTCH_API_KEY": "<TRUSTNOTCH_API_KEY>"
}
}
}
}{
"servers": {
"trustnotch-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"trustnotch-mcp"
],
"env": {
"TRUSTNOTCH_API_KEY": "<TRUSTNOTCH_API_KEY>"
}
}
}
}Put your own value in place of
<TRUSTNOTCH_API_KEY> (TrustNotch API key (tn_live_... or tn_test_...)).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
TRUSTNOTCH_API_URL (Base URL of the TrustNotch API), TRUSTNOTCH_PUBKEYS_PATH (Path to a local public-key file to pin for independent offline verification).
Alternatives to TrustNotch
same job, measured the same wayTamper-evident proof creation and verification for AI agents via MCP, A2A, and REST.
Bitcoin-anchored, tamper-evident audit log for AI agents — record, disclose and verify actions.
Causal memory and tamper-evident audit log for AI agents: log, why, search, time travel.
Credential vault for AI agents — Fernet-encrypted keys, per-agent budgets, audit logs.
Verifiable cognition: prove a session ledger is tamper-evident; audit & import any agent's logs.
Pre-execution gate for AI-agent tool calls. Touch ID approval. Tamper-evident audit log.
Commit-time policy checks for AI agent writes (ALLOW/DENY/STEP_UP) with a tamper-evident audit log.
Commit-time policy checks for AI agent writes (ALLOW/DENY/STEP_UP) with a tamper-evident audit log.
TrustNotch — questions
Answers built from our own checks of this server.