Agent Guardrail MCP Server runs on your own machine — the client starts it, so there is no endpoint to ping. 81 installs a week from pypi. Last commit 21 Mar 2026.
Action-level governance for AI agents -- control what they DO, not what they SAY
Today is the operative word: we check Agent Guardrail MCP Server 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-guardrail -- uvx agent-guardrail
{
"mcpServers": {
"agent-guardrail": {
"args": [
"agent-guardrail"
],
"command": "uvx"
}
}
}
[mcp_servers.agent-guardrail]
command = "uvx"
args = ["agent-guardrail"]
{
"mcpServers": {
"agent-guardrail": {
"args": [
"agent-guardrail"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"agent-guardrail": {
"args": [
"agent-guardrail"
],
"command": "uvx"
}
}
}
AI governance MCP server: trust scoring, guardrails, bias/hallucination detection, compliance.
Kubernetes MCP server with RBAC-style, context-scoped guardrails for AI agents.
AI governance MCP server for policy enforcement, cost control, and observability.
Open-source MCP server for AI agents: web search, content extraction, and library docs.
MCP server giving AI agents one-connection access to labor & financial-compliance data: DOL Form 550
AI governance MCP server for EU AI Act compliance and jurisdiction verification
Agentic SDLC governance and security controls for AI coding agents working with GitHub.
MCP server for Godot game engine integration — control the Godot editor with AI
Answers built from our own checks of this server.