MCP Imagenate

Please install the `mcp-imagenate` MCP server into my current AI client (that's you).

Required prerequisites (do these first if not already done):
- **At least one provider API key** — Get an API key from Google AI Studio, OpenAI, or BFL (FLUX)

Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["mcp-imagenate"]
- optional environment variables:
  - `GEMINI_API_KEY`: Google AI Studio API key (Gemini / Nano Banana) (example: `<your-api-key>`)
  - `OPENAI_API_KEY`: OpenAI API key (gpt-image-1.5) (example: `<your-api-key>`)
  - `BFL_API_KEY`: BFL FLUX API key (example: `<your-api-key>`)
  - `NANO_BANANA_OUTPUT_DIR`: Base directory for saved images (enables path sandboxing) (example: `/path/to/image/output`)

Note: Multi-provider image generation (Google Gemini, OpenAI, BFL FLUX). At least one provider API key must be set. Node.js 18+.

Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.