Skip to content
mcp/harbor
Gemini CLI

gency mcp for Gemini CLI

ai.gency/gency-mcp

Gency AI product image generation - MCP server for Claude, Codex, Cursor, VS Code

client:Gemini CLI transport:stdio runtime:npm

Install gency mcp 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": {
    "gency-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@gency-ai/gency-mcp"
      ],
      "env": {
        "GENCY_API_URL": "<GENCY_API_URL>",
        "GENCY_OAUTH_CLIENT_ID": "<GENCY_OAUTH_CLIENT_ID>",
        "GENCY_OAUTH_CLIENT_SECRET": "<GENCY_OAUTH_CLIENT_SECRET>",
        "GENCY_OAUTH_API_BASE": "<GENCY_OAUTH_API_BASE>",
        "GENCY_OAUTH_SCOPE": "<GENCY_OAUTH_SCOPE>",
        "GENCY_MCP_ALLOWED_CLIENT_IDS": "<GENCY_MCP_ALLOWED_CLIENT_IDS>",
        "GENCY_MCP_UPLOAD_SECRET": "<GENCY_MCP_UPLOAD_SECRET>",
        "GENCY_MCP_OAUTH_RESOURCE": "<GENCY_MCP_OAUTH_RESOURCE>"
      }
    }
  }
}

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

gency mcp in other clients

gency mcp MCP server