Yagami AI Context Firewall for VS Code

io.github.matthewtracy/yagami

Govern model, retrieval, memory, and tool access for AI applications and agents.

client:VS Code transport:stdio runtime:pypi

Install Yagami AI Context Firewall in VS Code

.vscode/mcp.json

{
  "inputs": [
    {
      "type": "promptString",
      "id": "yagami-headless",
      "description": "YAGAMI_HEADLESS",
      "password": true
    },
    {
      "type": "promptString",
      "id": "yagami-mcp-server-enabled",
      "description": "YAGAMI_MCP_SERVER_ENABLED",
      "password": true
    },
    {
      "type": "promptString",
      "id": "yagami-require-auth",
      "description": "YAGAMI_REQUIRE_AUTH",
      "password": true
    }
  ],
  "servers": {
    "yagami": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "yagami"
      ],
      "env": {
        "YAGAMI_HEADLESS": "${input:yagami-headless}",
        "YAGAMI_MCP_SERVER_ENABLED": "${input:yagami-mcp-server-enabled}",
        "YAGAMI_REQUIRE_AUTH": "${input:yagami-require-auth}"
      }
    }
  }
}

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

Yagami AI Context Firewall in other clients

Yagami AI Context Firewall MCP server