safeagent

Name: safeagent
Author: azender1

azender1

Execution control layer for AI agents — prevents duplicate or incorrect real-world actions under retries, uncertainty, and stale context.

Setup

Choose your client, copy the config, then fill in any required environment variables.

claude mcp add safeagent -- uvx safeagent-exec-guard

~/.codex/config.toml

[mcp_servers.safeagent]
command = "uvx"
args = ["safeagent-exec-guard"]

# codex mcp add safeagent -- uvx safeagent-exec-guard

~/.cursor/mcp.json

{
  "mcpServers": {
    "safeagent": {
      "command": "uvx",
      "args": [
        "safeagent-exec-guard"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "safeagent": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "safeagent-exec-guard"
      ]
    }
  }
}

~/.gemini/settings.json

{
  "mcpServers": {
    "safeagent": {
      "command": "uvx",
      "args": [
        "safeagent-exec-guard"
      ]
    }
  }
}

claude_desktop_config.json

{
  "mcpServers": {
    "safeagent": {
      "command": "uvx",
      "args": [
        "safeagent-exec-guard"
      ]
    }
  }
}

.trae/mcp.json

{
  "mcpServers": {
    "safeagent": {
      "command": "uvx",
      "args": [
        "safeagent-exec-guard"
      ]
    }
  }
}