Agent Guard runs on your own machine — the client starts it, so there is no endpoint to ping. 35 installs a week from npm. Last commit 24 Apr 2026.
Constitutional guardrails and loop detection for AI agents
Today is the operative word: we check Agent Guard 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 agent-guard -- npx -y agent-guard-mcp
{
"mcpServers": {
"agent-guard": {
"args": [
"-y",
"agent-guard-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.agent-guard]
command = "npx"
args = ["-y", "agent-guard-mcp"]
{
"mcpServers": {
"agent-guard": {
"args": [
"-y",
"agent-guard-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"agent-guard": {
"args": [
"-y",
"agent-guard-mcp"
],
"command": "npx"
}
}
}
Constitutional-AI safety guardrails for any LLM — personas, constitutions, adjudication.
Local-first project memory and mistake-prevention guardrails for AI coding agents.
Static linter for CLAUDE.md-style agent constitution files: 10 operational-guardrail checks.
Static linter for CLAUDE.md-style agent constitution files: 10 operational-guardrail checks.
Security guardrails for AI agent payments
Local-first control plane for coding agents: routing, reservations, and guardrails.
Stateful memory for AI agents. Temporal awareness, error loop detection, and preventive constraints.
Security scanning and threat detection for AI agents
Answers built from our own checks of this server.