A
licenseA
qualityD
maintenanceExposes Google Gemini's Nano Banana image generation models to Claude, enabling text-to-image generation, image editing, and multi-image composition through natural language prompts.
3
MIT
frameflow-mcp
by msaeedsakib
Provides tools for generating and editing images and videos using Google's Gemini (Nano Banana, Omni) and Veo 3.1 models via Google Cloud's AI Platform.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@frameflow-mcpgenerate an image of a futuristic city at night"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
frameflow-mcp
MCP server for Google's image and video models on your own Google Cloud project: Nano Banana (Gemini image models), Gemini Omni and Veo 3.1. One command stores a service account key and wires the server into Claude Code, Cursor and Codex.
Install
npx @saeedsakib/frameflow-mcp setupThe wizard asks for your service account JSON key, verifies access, and installs the server plus a skill into the agents you pick. Restart your agent afterwards.
Other commands:
Command | What it does |
| Show the stored key, configured agents and verify access |
| Remove the server and skill from agents, optionally delete the key |
| Run the stdio MCP server (what your agent runs) |
Any other MCP client:
{ "mcpServers": { "frameflow": { "command": "npx", "args": ["-y", "@saeedsakib/frameflow-mcp"] } } }Related MCP server: MCP Google Vertex AI Server
Google Cloud setup
Create or pick a project with billing enabled.
Enable the Gemini Enterprise Agent Platform API (
aiplatform.googleapis.com).Create a service account, grant it Agent Platform User (
roles/aiplatform.user), and download a JSON key.Run
setupand point it at the key. The file is copied to~/.config/frameflow-mcp/service-account.jsonwith owner-only permissions; you can delete the download.
Tools
Every generating tool writes to a local output_path and returns it. Video tools return a job_id immediately; poll get_video_job until it is done.
Tool | Models | Purpose |
| Allowed model ids per tool and the current defaults | |
| Persist a default model for a tool | |
| Nano Banana | Text to image |
| Nano Banana | Edit or compose with up to 14 reference images |
| Omni, Veo | Text to video |
| Omni, Veo | Image to video |
| Omni, Veo | Reference images and/or first and last frames |
| Omni | Continue a clip by up to 10 seconds |
| Omni | Edit a clip by prompt |
| Poll a job; downloads the file when finished |
No default model is built in. Ask your agent to pick defaults once (list_models then set_default_model); they are stored in ~/.config/frameflow-mcp/config.json.
Model ids: gemini-3.1-flash-image, gemini-3-pro-image, gemini-3.1-flash-lite-image, gemini-omni-1.1-flash-preview, veo-3.1-generate-001, veo-3.1-fast-generate-001.
Where things are written
Path | Contents |
|
|
| Claude Code MCP entry |
| Claude Code skill |
| Cursor |
| Codex |
License
MIT
Related MCP Connectors
Generate AI images, video, voiceovers and music from Claude, ChatGPT or Cursor through 50+ models (Veo 3.1, Kling 3, Seedance, Nano Banana, GPT Image, ElevenLabs). Also image editing, upscaling, background removal, face swap, transcription, voice cloning and UGC-style video ads. Sign in with OAuth — no API key to paste. Tools are annotated (read-only vs. credit-spending); failed generations are refunded.
Generate AI images, video, speech, music and presentations from Claude, ChatGPT and Cursor.
LLM chat, text tools, image generation, editing, batch image jobs, and asynchronous video generation
Image and video AI tools and your own pipelines, run from any AI assistant.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI image and video generation using Google Vertex AI's Imagen and Veo models, with support for configurable parameters and local storage.1MIT
- AlicenseAqualityDmaintenanceEnables Claude Code to generate, edit, blend, and create variations of images using BytePlus SeeDream AI models, with streaming and Firebase sync.6MIT
- FlicenseNot gradedqualityDmaintenanceEnables Claude to generate and edit images using Google Gemini AI.-