Agentos runs on your own machine — the client starts it, so there is no endpoint to ping. 27 installs a week from npm. Last commit 3 Mar 2026.
Build and manage policy-compliant AI agents with safety enforcement and compliance checking
The author archived this repository on GitHub, meaning it is no longer maintained.
We read the source, 21 h ago · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
chrome.devtools.inspectedWindow.eval(`
result = eval(code, {"__builtins__": {}}, namespace)
result = subprocess.run(cmd, capture_output=True, text=True)
"!pip install agent-os --quiet"
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
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 agentos -- npx -y agentos-mcp-server
{
"mcpServers": {
"agentos": {
"args": [
"-y",
"agentos-mcp-server"
],
"command": "npx"
}
}
}
[mcp_servers.agentos]
command = "npx"
args = ["-y", "agentos-mcp-server"]
{
"mcpServers": {
"agentos": {
"args": [
"-y",
"agentos-mcp-server"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"agentos": {
"args": [
"-y",
"agentos-mcp-server"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
AGENTOS_POLICY_MODE (Policy enforcement mode: strict (block all violations) or permissive (warn only)), AGENTOS_LOG_LEVEL (Log level: debug, info, warn, or error).
The author declared them in the registry entry; get the values from the project itself.
AI agent governance for MCP: PII detection, policy enforcement, compliance, and kill switch.
EU AI Act and GDPR compliance: checks, audits, generate policies.
Process management and monitoring for AI agents with strict security boundaries
Cordon for MCP. Security gateway with policy enforcement, audit log, and HITL approvals.
MCP server for npm package management, security analysis, and compatibility checking
x402 payment safety for AI agents: counterparty risk gate, payment firewall, compliance, RWA gate.
EU AI Act compliance scanner for Python AI agents — scan, analyze, and remediate
Governance runtime for AI agents with signed provenance, compliance audits, and OSINT.
Answers built from our own checks of this server.