What runtime does Claude Code Guardian require?
It requires Node.js and is installed as a global npm package (`codeguardian-studio`).
@phuongrealmax
基本信息
AI-Safe Code Analysis with 113+ MCP tools - guard, memory, workflow, testing, latent chain
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"claude-code-guardian": {
"command": "npx",
"args": [
"-y",
"codeguardian-studio"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。
Claude Code Guardian is an MCP server providing 113+ AI-safe code analysis tools for Claude Code and other MCP clients. It includes guard modules for code validation, persistent memory, task workflows, automated testing, code optimization, multi-phase reasoning, and session management.
Install globally with npm install -g codeguardian-studio, then add the server configuration to your Claude Desktop config. The server is invoked via npx -y codeguardian-studio as an MCP command.
It requires Node.js and is installed as a global npm package (`codeguardian-studio`).
Add the server entry to the `mcpServers` object in the Claude Desktop configuration file, using `npx -y codeguardian-studio` as the command.
Yes, the README states it works with Claude Code and other MCP clients.
The server provides 113+ tools for code analysis, testing, workflow, and session management.
Persistent knowledge is stored across sessions, but the README does not specify storage location or retention limits.

Agent-Native Terminal

Email security and AI discoverability scores for any domain, with the exact DNS record or tag to fix. Five read-only tools, no account or key needed.
Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.
评论