Tanilo runs on your own machine — the client starts it, so there is no endpoint to ping. 363 installs a week from npm. Last commit 13 Oct 2026.
Tanilo checks the premise before an AI agent acts.
Today is the operative word: we check Tanilo 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 tanilo-mcp -- npx -y tanilo-mcp
{
"mcpServers": {
"tanilo-mcp": {
"args": [
"-y",
"tanilo-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.tanilo-mcp]
command = "npx"
args = ["-y", "tanilo-mcp"]
{
"mcpServers": {
"tanilo-mcp": {
"args": [
"-y",
"tanilo-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"tanilo-mcp": {
"args": [
"-y",
"tanilo-mcp"
],
"command": "npx"
}
}
}
Ask Vulnify before an AI agent acts. Check, record, and read policy decisions.
The trust harness for AI agents. Set what an agent can do before it acts.
Checks a counterparty before an AI agent pays: what the evidence supports, and for how much.
Verify x402 payment endpoints before an AI agent pays: scam scan, on-chain checks, trust scores.
Free, local check before an AI agent acts: your rules return ACT, BLOCK or ESCALATE.
Pre-send risk check for AI agents that move money — screen an address or payment URL before sending.
Check an email before an AI agent sends it: send / ask a human / block. Detects prompt injection.
Meter, cap, and block AI agent spend before the provider is charged.
Answers built from our own checks of this server.