@saeedsakib/frameflow

GitHub Actions

MCP server for Google image and video models (Nano Banana, Gemini Omni, Veo) on Gemini Enterprise Agent Platform, with a one-command service account setup for Claude Code, Cursor and Codex

Devops Developer Tools

Add to Cursor Add to VS Code Run on PlugMCP

GitHub npm Website

Add to Cursor Add to VS Code Run on PlugMCP

1{2  "mcpServers": {3    "saeedsakib-frameflow-mcp": {4      "command": "npx",5      "args": [6        "-y",7        "@saeedsakib/[email protected]"8      ]9    }10  }11}

.cursor/mcp.jsonMCP server

Transport: stdio
Status: Local

Power your agent

Add this server

The publisher's own command. Not a PlugMCP endpoint.

Add to Cursor Add to VS Code Run on PlugMCP

Host a copy with our keys and logs.

Local command

npx -y @saeedsakib/[email protected]

Claude Code has no install link for a local command. Copy the command below and run it in a terminal.

shClaude Code

1claude mcp add saeedsakib-frameflow-mcp -- npx -y @saeedsakib/frameflow-mcp@0.2.0

Run in a terminal.

jsonClaude Desktop

1{2  "mcpServers": {3    "saeedsakib-frameflow-mcp": {4      "command": "npx",5      "args": [6        "-y",7        "@saeedsakib/[email protected]"8      ]9    }10  }11}

claude_desktop_config.json

Local · npmPublisher installStep-by-step: add this in Claude

Remote URL or a command on your machine? How the two installs differ

Run on PlugMCP

Host a copy with our keys and logs.

A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.

Launch

Server facts

Local

Transport: stdio
Version: 0.2.0
Last checked: 2026-10-28

Stars: —
Tools: —
Uptime: —

Tools

No tool list yet. Remote servers get one after the first health check.

FAQ

Questions

How do I install @saeedsakib/frameflow?

Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.

Does @saeedsakib/frameflow need an API key?

No required environment variable is listed on this record.

What transport does @saeedsakib/frameflow use?

@saeedsakib/frameflow runs locally over stdio.

When was @saeedsakib/frameflow last checked?

Last checked 2026-10-28. MCP server for Google image and video models (Nano Banana, Gemini Omni, Veo) on Gemini Enterprise Agent Platform, with a one-command service account setup for Claude Code, Cursor and Codex

From the publisher

Documentation

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 setup

The 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
`npx @saeedsakib/frameflow-mcp status`	Show the stored key, configured agents and verify access
`npx @saeedsakib/frameflow-mcp remove`	Remove the server and skill from agents, optionally delete the key
`npx @saeedsakib/frameflow-mcp`	Run the stdio MCP server (what your agent runs)

Any other MCP client:

{ "mcpServers": { "frameflow": { "command": "npx", "args": ["-y", "@saeedsakib/frameflow-mcp"] } } }

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 setup and point it at the key. The file is copied to ~/.config/frameflow-mcp/service-account.json with 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
`list_models`		Allowed model ids per tool and the current defaults
`set_default_model`		Persist a default model for a tool
`generate_image`	Nano Banana	Text to image, optionally guided by up to 14 reference images (logos, products, characters, style)
`generate_video`	Omni, Veo	Text to video
`animate_image`	Omni, Veo	Image to video
`generate_video_from_references`	Omni, Veo	Reference images and/or first and last frames
`extend_video`	Omni	Continue a clip by up to 10 seconds
`edit_video`	Omni	Edit a clip by prompt
`get_video_job`		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
`~/.config/frameflow-mcp/` (or `$XDG_CONFIG_HOME`, `%APPDATA%` on Windows)	`service-account.json`, `config.json`
`~/.claude.json` (or `$CLAUDE_CONFIG_DIR/.claude.json`)	Claude Code MCP entry
`~/.claude/skills/frameflow-mcp/`	Claude Code skill
`~/.cursor/mcp.json`, `~/.cursor/skills/frameflow-mcp/`	Cursor
`~/.codex/config.toml` (or `$CODEX_HOME`), `~/.agents/skills/frameflow-mcp/`	Codex

License

MIT

@saeedsakib/frameflow

GitHub Actions

MCP server for Google image and video models (Nano Banana, Gemini Omni, Veo) on Gemini Enterprise Agent Platform, with a one-command service account setup for Claude Code, Cursor and Codex

Devops Developer Tools

Add to Cursor Add to VS Code Run on PlugMCP

GitHub npm Website

Add to Cursor Add to VS Code Run on PlugMCP

1{2  "mcpServers": {3    "saeedsakib-frameflow-mcp": {4      "command": "npx",5      "args": [6        "-y",7        "@saeedsakib/[email protected]"8      ]9    }10  }11}

.cursor/mcp.jsonMCP server

Transport: stdio
Status: Local

Power your agent

Add this server

The publisher's own command. Not a PlugMCP endpoint.

Add to Cursor Add to VS Code Run on PlugMCP

Host a copy with our keys and logs.

Local command

npx -y @saeedsakib/[email protected]

Claude Code has no install link for a local command. Copy the command below and run it in a terminal.

shClaude Code

1claude mcp add saeedsakib-frameflow-mcp -- npx -y @saeedsakib/frameflow-mcp@0.2.0

Run in a terminal.

jsonClaude Desktop

1{2  "mcpServers": {3    "saeedsakib-frameflow-mcp": {4      "command": "npx",5      "args": [6        "-y",7        "@saeedsakib/[email protected]"8      ]9    }10  }11}

claude_desktop_config.json

Local · npmPublisher installStep-by-step: add this in Claude

Remote URL or a command on your machine? How the two installs differ

Run on PlugMCP

Host a copy with our keys and logs.

A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.

Launch

Server facts

Local

Transport: stdio
Version: 0.2.0
Last checked: 2026-10-28

Stars: —
Tools: —
Uptime: —

Tools

No tool list yet. Remote servers get one after the first health check.

FAQ

Questions

How do I install @saeedsakib/frameflow?

Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.

Does @saeedsakib/frameflow need an API key?

No required environment variable is listed on this record.

What transport does @saeedsakib/frameflow use?

@saeedsakib/frameflow runs locally over stdio.

When was @saeedsakib/frameflow last checked?

From the publisher

Documentation

frameflow-mcp

Install

npx @saeedsakib/frameflow-mcp setup

The 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
`npx @saeedsakib/frameflow-mcp status`	Show the stored key, configured agents and verify access
`npx @saeedsakib/frameflow-mcp remove`	Remove the server and skill from agents, optionally delete the key
`npx @saeedsakib/frameflow-mcp`	Run the stdio MCP server (what your agent runs)

Any other MCP client:

{ "mcpServers": { "frameflow": { "command": "npx", "args": ["-y", "@saeedsakib/frameflow-mcp"] } } }

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 setup and point it at the key. The file is copied to ~/.config/frameflow-mcp/service-account.json with 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
`list_models`		Allowed model ids per tool and the current defaults
`set_default_model`		Persist a default model for a tool
`generate_image`	Nano Banana	Text to image, optionally guided by up to 14 reference images (logos, products, characters, style)
`generate_video`	Omni, Veo	Text to video
`animate_image`	Omni, Veo	Image to video
`generate_video_from_references`	Omni, Veo	Reference images and/or first and last frames
`extend_video`	Omni	Continue a clip by up to 10 seconds
`edit_video`	Omni	Edit a clip by prompt
`get_video_job`		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
`~/.config/frameflow-mcp/` (or `$XDG_CONFIG_HOME`, `%APPDATA%` on Windows)	`service-account.json`, `config.json`
`~/.claude.json` (or `$CLAUDE_CONFIG_DIR/.claude.json`)	Claude Code MCP entry
`~/.claude/skills/frameflow-mcp/`	Claude Code skill
`~/.cursor/mcp.json`, `~/.cursor/skills/frameflow-mcp/`	Cursor
`~/.codex/config.toml` (or `$CODEX_HOME`), `~/.agents/skills/frameflow-mcp/`	Codex

License

MIT