Agent Guardrails runs on your own machine — the client starts it, so there is no endpoint to ping. 125 installs a week from npm.
Merge gates and safety checks for AI coding agents via MCP.
Today is the operative word: we check Agent Guardrails 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-guardrails -- npx -y agent-guardrails
{
"mcpServers": {
"agent-guardrails": {
"args": [
"-y",
"agent-guardrails"
],
"command": "npx"
}
}
}
[mcp_servers.agent-guardrails]
command = "npx"
args = ["-y", "agent-guardrails"]
{
"mcpServers": {
"agent-guardrails": {
"args": [
"-y",
"agent-guardrails"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"agent-guardrails": {
"args": [
"-y",
"agent-guardrails"
],
"command": "npx"
}
}
}
Policy-as-code guardrails for AI coding agents, validated via OPA, Conftest, Checkov & Semgrep.
Structured execution for coding agents: contracts, postconditions, gates, guardrails.
Local-first project memory and mistake-prevention guardrails for AI coding agents.
Security guardrails for AI agent payments
Local MCP server for AI coding safety: risk checks, sessions, checkpoints, and fix prompts.
Sanctions screening and PEP checks via OpenSanctions API for AI agents
Evidence-gated verification, selection, and measurement MCP for coding agents.
Constitutional guardrails and loop detection for AI agents
Answers built from our own checks of this server.