Nanobanana MCP server

@nanobanana/mcp 🍌

A lean MCP server for Google's Nano Banana (Gemini) image models and Veo video models. It generates and edits images and generates video from any MCP client (Claude Code, Claude Desktop, Cursor) and hands back file paths instead of base64, so your agent's context stays small.

• Six tools and nothing else: generateimage, editimage, generatevideo, extendvideo, getvideoresult, list_models
• Defaults to Nano Banana 2 (gemini-3.1-flash-image) and Veo 3.1 Fast (veo-3.1-fast-generate-preview). Switch models per call or via env. If a pinned model id ever goes stale, list_models shows what your key can actually use.
• Multi-image editing: pass reference images for style transfer, characters, or compositing
• Control over aspect ratio (1:1 through 21:9, out to 1:4 and 8:1) and resolution (512, 1K, 2K, 4K)
• Google Search grounding for images that need real-world accuracy, like infographics
• Video as a job, not a blocked call: generation takes 1–6 min, so generatevideo returns a job id and getvideo_result polls within every client's 60s timeout
• Safe output paths. The server never writes to / when a desktop MCP client spawns it there.
• Auth lives in env vars only, so your API key never passes through chat context

Quick start

Get a free Gemini API key at aistudio.google.com/apikey.

Claude Code

claude mcp add nanobanana -e GEMINI_API_KEY=your_key -- npx -y @nanobanana/mcp

Also listed in the MCP Registry as io.github.getjoystick/nanobanana-mcp.

Claude Desktop / Cursor: add this to claudedesktopconfig.json or .cursor/mcp.json:

{
  "mcpServers": {
    "nanobanana": {
      "command": "npx",
      "args": ["-y", "@nanobanana/mcp"],
      "env": { "GEMINI_API_KEY": "your_key" }
    }
  }
}

Tools

generate_image

edit_image

Same params, plus:

Both tools save to disk and return the file path.

list_models

Takes no params. Lists the image and video model ids your API key can use, in two sections. Handy when a pinned model id stops working, which is how earlier Nano Banana servers broke — and Veo's ids are previews that will be renamed.

Video

Veo generation takes 1–6 minutes, and MCP clients kill a tool call at ~60s. So video is a job: you start one, then poll.

generate_video   →  "Video job started: <jobId>"
get_video_result →  "Still processing (<jobId>)…"   ← blocks up to 45s, then call again
get_video_result →  "Saved: /path/to/clip.mp4 (veo-3.1-fast-generate-preview)
                     Veo URI (needed for extend_video; expires ~2 days): https://…"

getvideoresult does the waiting for you — each call blocks up to waitSeconds (45 by default, the most that fits inside a client's 60s timeout). Call it right away and call it again the moment it returns; there is no need to pause in between, which matters because an agent has no way to sleep.

Shortened. The full README is on GitHub.