ai agent firewall for VS Code

com.fidacy/ai-agent-firewall

Every agent action watched, every money-moving one gated, every verdict independently verifiable.

client:VS Code transport:stdio runtime:npm

Install ai agent firewall in VS Code

.vscode/mcp.json

{
  "inputs": [
    {
      "type": "promptString",
      "id": "fidacy-engine-api-key",
      "description": "FIDACY_ENGINE_API_KEY",
      "password": true
    },
    {
      "type": "promptString",
      "id": "fidacy-operator-email",
      "description": "FIDACY_OPERATOR_EMAIL",
      "password": true
    },
    {
      "type": "promptString",
      "id": "fidacy-mode",
      "description": "FIDACY_MODE",
      "password": true
    }
  ],
  "servers": {
    "ai-agent-firewall": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@fidacy/mcp"
      ],
      "env": {
        "FIDACY_ENGINE_API_KEY": "${input:fidacy-engine-api-key}",
        "FIDACY_OPERATOR_EMAIL": "${input:fidacy-operator-email}",
        "FIDACY_MODE": "${input:fidacy-mode}"
      }
    }
  }
}

VS Code prompts for each input the first time the server starts, so no secret is written to the file. VS Code docs

ai agent firewall in other clients

ai agent firewall MCP server