TrigGuard runs on your own machine — the client starts it, so there is no endpoint to ping. 210 installs a week from npm.
Execution authorization for AI agents and automated systems.
The linked repository no longer exists on GitHub — it was deleted or made private.
Quiet is not dead — but it is worth knowing when it wakes up, or when someone else takes it over. We watch the repository and tell you either way.
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 trigguard -- npx -y @trigguard/mcp-server
{
"mcpServers": {
"trigguard": {
"args": [
"-y",
"@trigguard/mcp-server"
],
"command": "npx"
}
}
}
[mcp_servers.trigguard]
command = "npx"
args = ["-y", "@trigguard/mcp-server"]
{
"mcpServers": {
"trigguard": {
"args": [
"-y",
"@trigguard/mcp-server"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"trigguard": {
"args": [
"-y",
"@trigguard/mcp-server"
],
"command": "npx"
}
}
}
Structured execution trace and span logging for AI agents
A trusted local encrypted execution boundary for AI agents.
Safe BLE diagnostics, evidence workflows, and guarded automation for AI agents.
MCP adapter for Agent_Sudo: authorization, delegation, provenance, and audit for AI agents.
Record and replay AI agent execution for debugging
Intent-bound action authorization for AI agents: policy, human approval, and a signed audit trail.
Verifiable execution for AI agents: Ed25519-signed work contracts and audit trails.
Security gateway for AI agents: policy, approval, and audited execution, no secrets shared.
Answers built from our own checks of this server.