agent-sec
Zero-install security baseline for AI coding agents — OWASP/CWE-cited rules over MCP.
我该使用它吗
质量与安全性
B
发现(1)
- LOW在 get_security_baseline 中
基于对工具定义和协议合规性的自动分析。
上下文开销
~168token 数(工具定义)
~243 B典型响应大小
对注意力的影响极小(占 128k 上下文窗口的 0.13%)
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高,可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中:
{
"mcpServers": {
"agent-sec": {
"url": "https://agentsec.kernora.ai/mcp"
}
}
}远程端点
https://agentsec.kernora.ai/mcpstreamable-http它能做什么
工具清单
工具(2)
🟢 只读🟡 写入🔴 删除⚪ 未知
🟢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.
输入模式
{
"type": "object",
"properties": {}
}🟢check_action(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 Security's paid Integrity Plane.
输入模式
{
"type": "object",
"properties": {
"action": {
"type": "string",
"description": "the action/command about to run"
}
},
"required": [
"action"
]
}推荐提示词
retrieve_data
Get details about [item] from agent-sec
预期工具:
get_security_baselinefetch_info
Fetch [information type] using agent-sec
预期工具:
get_security_baseline社区
证据
最近观测
已验证未记录版本2 个工具
已验证未记录版本2 个工具