AI Guardian runs on your own machine — the client starts it, so there is no endpoint to ping. 322 installs a week from pypi. Last commit 16 Sep 2026.
Governed local-LLM observability: model policy, prompt scanner, capture proxy, 21 tools.
Today is the operative word: we check AI Guardian 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 ai-guardian -- uvx ai-guardian-aiops
{
"mcpServers": {
"ai-guardian": {
"args": [
"ai-guardian-aiops"
],
"command": "uvx"
}
}
}
[mcp_servers.ai-guardian]
command = "uvx"
args = ["ai-guardian-aiops"]
{
"mcpServers": {
"ai-guardian": {
"args": [
"ai-guardian-aiops"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"ai-guardian": {
"args": [
"ai-guardian-aiops"
],
"command": "uvx"
}
}
}
Governed Prometheus + Grafana ops: PromQL, alerts, dashboards, RCA; 39 tools.
AI governance MCP server for policy enforcement, cost control, and observability.
Scan prompts, tool definitions and model output for injection, and guard agent tool calls.
Scan AI agents for tool-calling vulnerabilities: prompt leaks, hijacking, injections, and more.
Turn-level governance observability for Claude Code transcripts. Local-first, no LLM inside.
AI-powered SRE observability for Kubernetes/OpenShift with 40+ Tekton debugging tools
MCP control plane: local server discovery, profiles, capability bundles, and policy audits.
Paid Capture and Guard tools for public-source observations before autonomous actions.
Answers built from our own checks of this server.