google-flow-mcp
The server is an MCP controller for Google Flow that enables AI-powered asset generation (images, videos, characters, storyboards) with local folder storage and project management. Key capabilities include:
Account & Flow Management: Connect Google account, check credits/limits, list projects and custom tools.
Image Generation: Create single/batch images with models like NARWHAL or GEMMA_2; control aspect ratio, seeds, negative prompts; upscale to 4K.
Video Generation: Generate text-to-video (Veo 3.1/Gemini Omni) and image-to-video animations; requires spend confirmation with credit limits.
Character Consistency: Create reusable character cards and generate images featuring those characters for consistent faces.
Dossier & Storyboard Workflows: Upload character/worldbuilding dossiers; generate scenes, storyboards, and trailer scripts; render approved trailers.
Custom Tools: Execute, update, and audit custom or shared Google Flow tools (e.g., Storyboard Studio).
Local Storage: Save media to local folders, automatically scaffold book project directories (characters, props, etc.).
Safety: Spend guarding for video tools, max credits/generations settings.
Provides tools for generating images with Nano Banana/ImageFX, generating videos with Veo 3.1 and Gemini Omni, upscaling resolution, and managing character assets through Google Flow using your own Google account.
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., "@google-flow-mcp Generate an image of a cozy cabin in snowy mountains"
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.
Google Flow MCP (V2 Controller)
Self-hosted Model Context Protocol (MCP) server for Google Flow (labs.google/fx/tools/flow), refactored into a lean controller for book and story asset generation pipelines.
Authenticate with your own Google account to generate character candidates, props, places, scenes, and video clips—saving all outputs directly to your local file system or external drive (/Volumes/Xstorage/...).
Production Workflow Architecture
This MCP operates strictly as a controller for Google Flow asset creation:
Approved dossier
→ create book project
→ Storyboard Studio
→ characters / places / props / scenes
→ download candidates
→ approve stills
→ Veo / Omni animation
→ download clips
→ MiniMax
→ Remotion / CapCutThis MCP server is a thin Google Flow controller layer. It doesNOT handle full dossier truth systems, final trailer scripting strategy, MiniMax orchestration, Remotion assembly, CapCut rendering, or video publishing. Those operations belong outside this repository in the primary Immerse pipeline.
Related MCP server: flow-mcp
Key Principles & Scope
🎯 Google Flow Controller: Pure control layer for authenticating, listing/creating projects, executing Storyboard Studio/custom tools, generating media, and downloading assets locally.
🔒 Spend Guard & Budget Safety: Video generation tools (
generate_videoandgenerate_video_from_image) strictly requireconfirm_spend: trueto prevent accidental credit consumption. Supportsmax_creditsandmax_generationslimits.📂 Local Storage Integration: Auto-scaffolds clean book folder structures (
/characters,/props,/places,/scenes,/clips) on local or external drives.🤝 Pipeline Handoff: Decoupled from final trailer editing or assembly. Assets are saved cleanly for handoff to external tools (MiniMax, Remotion, CapCut).
🔐 Isolated Auth & Safety: Session credentials are kept strictly isolated and stored locally with restricted
0600file permissions.
Installation & Setup
1. Build Server
git clone https://github.com/LeoSzn12/google-flow-mcp.git
cd google-flow-mcp
npm install
npm run build2. Environment Configuration
Copy .env.example to .env:
cp .env.example .envSet your session credentials and local output root:
GOOGLE_COOKIES="your_google_cookies_string"
LOCAL_STORAGE_ROOT="/Volumes/Xstorage/Media"Available MCP Tools (V2)
Core Control Tools (14)
Tool Name | Description | Key Parameters |
| Check authentication state & account details |
|
| Save Google auth cookies or tokens |
|
| List Google Flow projects on your account | - |
| Create a new Google Flow project |
|
| List custom tools in a project |
|
| Execute custom tool or Storyboard tool |
|
| Generate image via NARWHAL / Nano Banana |
|
| Batch generate image candidates |
|
| Text-to-video via Veo 3.1 (Spend Guard) |
|
| Image-to-video keyframe animation (Spend Guard) |
|
| Query status of async generation jobs |
|
| Save generated media URL or ID to local disk |
|
| List all generated media items in session memory | - |
| Get details for a specific media item |
|
Thin Helper Tools (2)
Tool Name | Description | Key Parameters |
| Scaffold local book folder structure on disk |
|
| Execute Storyboard Studio with dossier input |
|
Integration Guides
Claude Code / Codex
claude mcp add --transport stdio google-flow -- node /absolute/path/to/google-flow-mcp/dist/index.jsCursor / Windsurf / Cline (mcpServers)
Add to ~/.cursor/mcp.json or .vscode/mcp.json:
{
"mcpServers": {
"google-flow": {
"command": "node",
"args": ["/absolute/path/to/google-flow-mcp/dist/index.js"],
"env": {
"GOOGLE_COOKIES": "your_google_cookies_string_here",
"LOCAL_STORAGE_ROOT": "/Volumes/Xstorage/Media"
}
}
}
}Happy Path Example Workflow (The Odyssey)
Here is how to run a complete asset pipeline workflow for an example book (The Odyssey):
1. Create a Book Project & Local Storage Folders
Call create_book_project:
{
"book_title": "The Odyssey",
"local_storage_root": "/Volumes/Xstorage/Media"
}Creates /Volumes/Xstorage/Media/the-odyssey/ with subfolders: characters/, props/, places/, scenes/, clips/.
2. Run Storyboard Studio with an Approved Dossier
Call run_storyboard_studio_from_dossier:
{
"book_title": "The Odyssey",
"dossier_text": "Odysseus: Weathered ancient Greek king and mariner, dark curly hair, bearded, wearing bronze-trimmed linen tunic, standing on rocky shore looking out at Aegean Sea.",
"asset_types": ["characters", "places", "scenes"],
"output_folder": "/Volumes/Xstorage/Media"
}Generates visual candidates and downloads stills directly into local project subfolders.
3. Animate Approved Keyframes into Video Clips
Call generate_video_from_image with explicit spend authorization:
{
"prompt": "Slow panning shot across Aegean sea waves crashing on rocky cliffs behind Odysseus",
"start_image_url": "/Volumes/Xstorage/Media/the-odyssey/characters/odysseus_still.png",
"confirm_spend": true,
"max_credits": 20,
"max_generations": 1,
"output_folder": "/Volumes/Xstorage/Media/the-odyssey/clips"
}Renders video using Google Veo 3.1 and saves flow_video_<timestamp>.mp4 to /clips.
4. Immerse Production Handoff
Hand off downloaded .png stills and .mp4 video clips to external assembly tools (MiniMax, Remotion, CapCut).
License
MIT
Available Tools
22 toolsaudit_custom_toolA
Audit the capabilities, parameters, models, and code logic of a Google Flow custom tool.
Inputs: tool_id (required).
batch_generate_imagesA
Generate multiple images in a single batch call using Google Flow Nano Banana Pro. More efficient than calling generate_image multiple times.
Inputs: prompts (required), model, aspect, account.
connect_google_accountA
Connect or update Google account credentials for Google Flow generation.
Inputs: cookies, bearerToken.
create_characterB
Create a reusable character card with consistent visual traits across multiple scenes.
Inputs: name (required), description (required), model.
flow_statusA
Check Google Flow connection status, active plan, remaining credits, and daily limits.
Inputs: account.
generate_from_dossierB
Generate high-fidelity artwork and scenes derived directly from an uploaded dossier (e.g. ACOTAR Feyre & Rhysand in Velaris).
Inputs: scene, aspect, prompt, character, +1 more.
generate_imageB
Generate a high-fidelity AI image using Google Flow (Nano Banana / NARWHAL models). Runs on your Google account.
Inputs: prompt (required), seed, count, model, +3 more.
generate_storyboardB
Create a multi-frame visual sequence using Google Flow Storyboard Studio tool.
Inputs: scenes (required), title.
generate_trailer_scriptA
Generate a viral 30-45 second social media (TikTok/Reels) cinematic book trailer script and storyboard keyframes for human review and approval.
Inputs: book_title (required), dossier_title, target_platform, target_duration_seconds.
generate_videoA
Generate an AI video from text using Google Flow (Veo 3.1 / Gemini Omni models).
Inputs: prompt (required), count, aspect, account, +2 more.
generate_video_from_imageA
Animate a static image into an AI video (Image-to-Video) using Google Veo 3.1.
Inputs: prompt (required), aspect, account, start_image_url, +2 more.
generate_with_faceA
Generate a new image featuring a saved character card to maintain face/subject consistency.
Inputs: prompt (required), character (required), aspect.
get_media_detailsA
Get detailed information about a specific generated media item.
Inputs: media_id (required).
list_mediaB
List all generated images and videos in the current session.
Inputs: no named parameters.
list_projectsA
List all Google Flow projects available on your account.
Inputs: no named parameters.
list_toolsB
List all custom tools available in a Google Flow project.
Inputs: project_id.
render_approved_trailer_videosA
Render the final Veo 3.1 video clips from approved storyboard keyframes and download them to your local media folder.
Inputs: approved_shots (required), output_folder.
run_custom_toolB
Execute a custom or shared Google Flow tool (e.g. Type Overlays, Video Resizer, Storyboard Studio, Shader Effects, Mockup, etc.) by tool ID or full URL.
Inputs: tool_id (required), inputs, prompt, project_id.
save_media_to_local_folderA
Save/download a generated image or video URL to a local folder on your computer.
Inputs: media_url_or_id (required), filename, output_folder.
update_custom_toolB
Edit or update the code, prompt instructions, or parameters of a custom Google Flow tool directly inside Google Flow.
Inputs: tool_id (required), name, project_id, description, +2 more.
upload_dossierC
Upload a character/worldbuilding dossier (such as ACOTAR characters, lore, and visual rules) to Google Flow.
Inputs: title (required), content, tool_id, dossier_path.
upscale_imageA
Upscale an image generated via Google Flow to high resolution (1K, 2K, 4K).
Inputs: media_id (required), target_resolution (required), account.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 22 tools
While most tools target distinct actions, several image/video generation tools (generate_image, batch_generate_images, generate_with_face, generate_from_dossier) overlap in the core generation action and could cause misselection. Storyboard generation also overlaps with the trailer script tool. However, the descriptions do differentiate inputs and use cases.
Tool names predominantly follow a verb_noun pattern (e.g., generate_image, list_projects, update_custom_tool). Minor variations like generate_with_face, generate_from_dossier, and save_media_to_local_folder deviate but remain readable and predictable.
At 22 tools, the server is on the heavier side of the recommended range. The breadth is justified by the mix of generation, character/dossier management, custom tool operations, and trailer workflow, but it still feels slightly over-scoped.
The tool surface covers the core media generation lifecycle, including account management, image/video generation, upscaling, character consistency, dossier-based generation, custom tool management, and media retrieval/saving. Missing operations are primarily deletion (e.g., no delete_character or delete_media) and character listing, but these are minor gaps.
Maintenance
Related MCP Connectors
MCP server for Google Veo AI video generation
MCP server for Qwen Image 3 AI image generation
MCP server for Hailuo (MiniMax) AI video generation
AI video generation MCP server for Kling, MiniMax, Luma & Hunyuan with prompt blueprints.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceMCP server for generating images and videos using Google Gemini and VEO models, with support for multiple AI models and credential modes.177 PyPI1Apache 2.0
- AlicenseAqualityCmaintenanceMCP server for generating images via Google Flow's API without daily quota limits, supporting text-to-image and image-to-image generation.11MIT
- AlicenseBqualityDmaintenanceA brand-neutral, self-hostable MCP server for generating and editing images using natural language, with support for reference images and multiple providers.1MIT
- AlicenseBqualityDmaintenanceMCP server that lets AI agents control Google Flow for generating images and videos using the user's own Google account. It provides tools for image generation, video creation, character and scene management, and UI discovery.171MIT