agent-runtime-guard

Agent runtime guard — full-stack runtime interception for AI agents (Agent 运行时全栈拦截). A zero-dependency MCP server that blocks destructive commands, credential theft, SSRF and injection in real time, with Ed25519 evidence receipts. Works with Claude Code,

Installation

MCP client config (paste into mcp.json)

{
  "mcpServers": {
    "npm-agent-runtime-guard": {
      "command": "npx",
      "args": [
        "agent-runtime-guard"
      ]
    }
  }
}

Agent install prompt

Copy and paste into Cursor / Claude / other agents to install this MCP for you

Please read this MCP repository and install it into my current environment:
https://www.npmjs.com/package/agent-runtime-guard

Known working client config (can write into mcp.json):
{
  "mcpServers": {
    "npm-agent-runtime-guard": {
      "command": "npx",
      "args": [
        "agent-runtime-guard"
      ]
    }
  }
}

Please: 1) check README for deps and env vars; 2) write config for my client; 3) if secrets are missing, tell me what to fill — do not invent values.

GitHub

Related servers