AI Runtime Guard
MCP Server
Blocks dangerous operations — rm -rf, sensitive file access, privilege escalation, and more are denied before execution. Gates risky commands behind human approval Simulates blast radius — wildcard operations like rm \*.tmp are evaluated before running Automatic backup of files Full audit of commands
工具数
快速接入
先看主来源和安装命令，再打开仓库或文档；下面只保留这个条目的关键接入事实。
目录标签
目录标签
接入字段
传输方式（transport，传输协议）
未说明
鉴权方式（authType，认证方式）
none
部署方式（deploymentType，部署类型）
local-only
权限和风险
接入前请确认传输方式、认证方式和部署位置，并根据实际工具能力限制访问范围。
不要直接授予不必要的文件、网络或账号权限；先核对安装命令和配置内容。
仍需确认：category / installCommand
来源信息
Glama
glama.ai
/mcp/servers/jimmyracheta/ai-runtime-guard
Blocks dangerous operations — rm -rf, sensitive file access, privilege escalation, and more are denied before execution. Gates risky commands behind human approval Simulates blast radius — wildcard operations like rm \*.tmp are evaluated before running Automatic backup of files Full audit of commands
Glama
glama.ai
/mcp/servers/runtimeguard/ai-runtime-guard
ai-runtime-guard is an MCP server that sits between your AI agent and your system, enforcing a policy layer before any file or shell action takes effect. No retraining, no prompt engineering, no changes to your agent or workflow, just install, configure once, and your agent operates within the boundaries you set.