Korg Ledger runs on your own machine — the client starts it, so there is no endpoint to ping. 284 installs a week from pypi. Last commit 23 Jun 2026.
Verifiable cognition: prove a session ledger is tamper-evident; audit & import any agent's logs.
We read the source, 21 h ago · rules 3dff92dd89df
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.
self._process = subprocess.Popen(
resolved = (os.path.join(root, path)
def exec(self, code: str, fuel: dict,
command, shell=True, input=json.dumps(payload),
env = dict(os.environ)
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
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.
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 korg-ledger -- uvx korgex
{
"mcpServers": {
"korg-ledger": {
"args": [
"korgex"
],
"command": "uvx"
}
}
}
[mcp_servers.korg-ledger]
command = "uvx"
args = ["korgex"]
{
"mcpServers": {
"korg-ledger": {
"args": [
"korgex"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"korg-ledger": {
"args": [
"korgex"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
KORG_JOURNAL_PATH (Path to the JSONL ledger journal (defaults to .korg/journal.jsonl).), KORG_LEDGER_HMAC_KEY (Optional HMAC key — makes the chain tamper-PROOF, not just tamper-evident.).
The author declared them in the registry entry; get the values from the project itself.
Tamper-evident audit logs for AI agents: submit, fetch, and verify cryptographic proof bundles.
Pre-execution gate for AI-agent tool calls. Touch ID approval. Tamper-evident audit log.
Append-only, signed, on-chain-verifiable agent action log — record and audit what agents did.
Verifiable action logs for AI agents. Every action is recorded in a SHA-256 hash chain.
Tamper-evident proof creation and verification for AI agents via MCP, A2A, and REST.
Tamper-evident action logging for agents: hash-chained append/verify, one JSONL file, zero deps.
Mine your local AI coding session logs into a profile your agent loads before every task.
Bitcoin-anchored, tamper-evident audit log for AI agents — record, disclose and verify actions.
Answers built from our own checks of this server.