MCP低风险未认领
Agent Guardrail MCP Server
Action-level governance for AI agents -- control what they DO, not what they SAY
JarvisOnM4jarvisonm4/agent-guardrail
server.json
{
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"name": "io.github.JarvisOnM4/agent-guardrail",
"description": "Action-level governance for AI agents -- control what they DO, not what they SAY",
"title": "Agent Guardrail MCP Server",
"repository": {
"url": "https://github.com/eren-solutions/agent-guardrail",
"source": "github",
"id": "1170171452"
},
"version": "0.1.2",
"websiteUrl": "https://github.com/eren-solutions/agent-guardrail",
"packages": [
{
"registryType": "pypi",
"registryBaseUrl": "https://pypi.org",
"identifier": "agent-guardrail",
"version": "0.1.2",
"transport": {
"type": "stdio"
}
}
]
}权限
声明检测
运行代码—
python安装—
pypi:agent-guardrail@0.1.2安装时运行脚本—无
网络无无
需要的凭据无无
工作区外的路径—无
智能体工具—无
检查
低风险 · 没有发现需要提醒的地方。
未经人工审核 · 已做规则检查;模型审核尚未开启。
版本
- #10.1.2最新2026年10月7日
Agent Guardrail MCP Server在 Codeg 中打开