Agent Sec is an MCP server with 2 tools an agent can call, among them check_action, get_security_baseline. It answers at https://agentsec.kernora.ai/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 4 September 2026; the last check, on 17 October 2026, succeeded.
Zero-install security baseline for AI coding agents — OWASP/CWE-cited rules over MCP.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
check_action | Advisory check: given a described action or command the agent is about to take, return the baseline security factlets that plausibly apply, so the agent can self-correct. Advisory only — does NOT block. Real-time blocking is Kernora Agent S Inputs: action |
get_security_baseline | Return Kernora Agent Security's curated security baseline — the known-good rules an AI coding agent should follow (secrets, injection, supply-chain, destructive ops, data protection). Advisory grounding. |
Every block below points at https://agentsec.kernora.ai/mcp. Pick your client and copy.
claude mcp add --transport http agent-sec https://agentsec.kernora.ai/mcp
{
"mcpServers": {
"agent-sec": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://agentsec.kernora.ai/mcp"]
}
}
}{
"mcpServers": {
"agent-sec": {
"url": "https://agentsec.kernora.ai/mcp"
}
}
}{
"servers": {
"agent-sec": {
"type": "http",
"url": "https://agentsec.kernora.ai/mcp"
}
}
}{
"context_servers": {
"agent-sec": {
"url": "https://agentsec.kernora.ai/mcp"
}
}
}{
"mcpServers": {
"agent-sec": {
"serverUrl": "https://agentsec.kernora.ai/mcp"
}
}
}{
"mcpServers": {
"agent-sec": {
"url": "https://agentsec.kernora.ai/mcp"
}
}
}name: Agent Sec
version: 0.0.1
schema: v1
mcpServers:
- name: Agent Sec
type: streamable-http
url: https://agentsec.kernora.ai/mcp{
"mcpServers": {
"agent-sec": {
"httpUrl": "https://agentsec.kernora.ai/mcp"
}
}
}{
"mcpServers": {
"agent-sec": {
"type": "http",
"url": "https://agentsec.kernora.ai/mcp"
}
}
}{
"mcpServers": {
"agent-sec": {
"url": "https://agentsec.kernora.ai/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fagentsec.kernora.ai%2Fmcp&type=streamable_http&id=agent-sec&name=Agent%20Sec
It answered our last check on 17 October 2026 in 125 ms. Over 10 checks since 4 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by kernora.ai and served from agentsec.kernora.ai, the vendor's own domain: https://agentsec.kernora.ai/mcp.
2, as returned by the server's own tools/list on 8 September 2026: check_action, get_security_baseline.
It answered our last check on 17 October 2026 in 125 ms. Over 10 checks since 4 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://agentsec.kernora.ai/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: ai.kernora. Endpoint host: agentsec.kernora.ai. ARD identifier: urn:air:ai.kernora:mcp:agent-sec.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.