Agent Guardrails runs on your own machine — the client starts it, so there is no endpoint to ping. 95 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": {
"command": "npx",
"args": [
"-y",
"agent-guardrails"
]
}
}
}
[mcp_servers.agent-guardrails]
command = "npx"
args = ["-y", "agent-guardrails"]
{
"mcpServers": {
"agent-guardrails": {
"command": "npx",
"args": [
"-y",
"agent-guardrails"
]
}
}
}
{
"servers": {
"agent-guardrails": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"agent-guardrails"
]
}
}
}
Policy-as-code guardrails for AI coding agents, validated via OPA, Conftest, Checkov & Semgrep.
Guardrails for AI coding agents: verified claims, reviews bound to exact commits, gated merges.
Structured execution for coding agents: contracts, postconditions, gates, guardrails.
Local OpenAPI contract and breaking-change checks for AI agents.
Local-first project memory and mistake-prevention guardrails for AI coding agents.
Security guardrails for AI agent payments
Local code graph and solution memory for coding agents via CLI and MCP.
Local MCP server for AI coding safety: risk checks, sessions, checkpoints, and fix prompts.
Answers built from our own checks of this server.