Skip to content
mcp/harbor
Gemini CLI

Exec Sandbox for Gemini CLI

io.github.inhuman/mcp-exec

Single exec tool running caller Python in a network-isolated locked-down sandbox.

client:Gemini CLI transport:stdio runtime:oci

Install Exec Sandbox in Gemini CLI

~/.gemini/settings.json · windows: %USERPROFILE%\.gemini\settings.json

Held in this page only — never stored, logged, or sent anywhere but back to your screen. 

{
  "mcpServers": {
    "mcp-exec": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "docker.io/idconstruct/mcp-exec:v0.5.4"
      ],
      "env": {
        "MCP_EXEC_TRANSPORT": "<MCP_EXEC_TRANSPORT>",
        "MCP_EXEC_DEFAULT_TIMEOUT_S": "<MCP_EXEC_DEFAULT_TIMEOUT_S>",
        "MCP_EXEC_MAX_TIMEOUT_S": "<MCP_EXEC_MAX_TIMEOUT_S>",
        "MCP_EXEC_MAX_OUTPUT_BYTES": "<MCP_EXEC_MAX_OUTPUT_BYTES>",
        "MCP_EXEC_MAX_STDIN_BYTES": "<MCP_EXEC_MAX_STDIN_BYTES>",
        "MCP_EXEC_AUTH_TOKEN": "<MCP_EXEC_AUTH_TOKEN>"
      }
    }
  }
}

Gemini expands $VAR and ${VAR} inside env values, so a secret can live in your shell rather than this file. Gemini CLI docs

Exec Sandbox in other clients

Exec Sandbox MCP server