Agent Sec is a Model Context Protocol (MCP) server: Zero-install security baseline for AI coding agents — OWASP/CWE-cited rules over MCP. In practice that means any MCP-compatible AI assistant can call Agent Sec's tools directly — the model decides when to use them in a conversation or agent run.
It's a hosted (remote) server — point your client at https://agentsec.kernora.ai/mcp and you're connected, with nothing to install locally. The current release is v0.1.0, published under the Apache-2.0 license, with source at kernora-ai/agent-sec on GitHub.
Agent Sec is listed under AI & Agents on mcp.site and works with any MCP client — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed and the rest of the ecosystem — using the install snippets below. If you maintain Agent Sec for kernora.ai, claim this listing to verify ownership, earn the Verified badge, and keep the details current.
