io.github.rudimentall1/agent-guardrail MCP Server

Name: io.github.rudimentall1/agent-guardrail MCP Server
Author: io.github.rudimentall1

io.github.rudimentall1/agent-guardrail

What is the io.github.rudimentall1/agent-guardrail MCP server?

Deterministic policy firewall for AI agent tool calls - YAML rules, not a fuzzy risk score.

Copy-paste configuration for popular MCP clients.

transport: stdio

Config generated by PluginBench — verify against the source before use.

Claude Desktop

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "agent-guardrail": {
      "command": "uvx",
      "args": [
        "guardrail-mcp"
      ]
    }
  }
}

Cursor

~/.cursor/mcp.json

{
  "mcpServers": {
    "agent-guardrail": {
      "command": "uvx",
      "args": [
        "guardrail-mcp"
      ]
    }
  }
}

Windsurf

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "agent-guardrail": {
      "command": "uvx",
      "args": [
        "guardrail-mcp"
      ]
    }
  }
}

VS Code

.vscode/mcp.json

{
  "servers": {
    "agent-guardrail": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "guardrail-mcp"
      ]
    }
  }
}

Claude Code

claude mcp add agent-guardrail -- uvx guardrail-mcp

Active

Explainable ALLOW/WARN/BLOCK risk decisions for AI agent actions before execution, signed as OAA.

Python

MIT