Kepil runs on your own machine — the client starts it, so there is no endpoint to ping. 247 installs a week from pypi. Last commit 25 Oct 2026.
Passport, mandate, fail-closed action gate and tamper-evident journal for AI agents.
We read the source, 22 h 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.
API = "https://api.telegram.org/bot{token}/{method}"
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 kepil -- uvx kepil
{
"mcpServers": {
"kepil": {
"command": "uvx",
"args": [
"kepil"
]
}
}
}
[mcp_servers.kepil]
command = "uvx"
args = ["kepil"]
{
"mcpServers": {
"kepil": {
"command": "uvx",
"args": [
"kepil"
]
}
}
}
{
"servers": {
"kepil": {
"type": "stdio",
"command": "uvx",
"args": [
"kepil"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
KEPIL_DATA (Directory for orders, passports, packs and the journal).
Local mandate gate and proof trail for AI agents that take consequential actions.
Tamper-evident proof creation and verification for AI agents via MCP, A2A, and REST.
Fail-closed human approval gates for AI agent actions. Default-deny, TTL expiry, audit log.
Pre-execution gate for AI-agent tool calls. Touch ID approval. Tamper-evident audit log.
Tamper-evident decision audit trail and outcome-weighted memory for AI trading agents.
Bitcoin-anchored, tamper-evident audit log for AI agents — record, disclose and verify actions.
Audits MCP and HTTPS calls. Tamper-evident trail for GLP.
Tamper-evident, Sigstore-signed audit trail for Claude Code agents.
Answers built from our own checks of this server.