Google Flow through the bridge

The bridge drives Google Flow in your own logged-in Chrome. Your agent sends a prompt and gets the reply text back, not the page.

host
labs.google
provider id
flow
default model
Veo 3.1
start page
https://labs.google/fx/tools/flow

What the bridge can do here

  • Send a prompt in your logged-in Chrome and read the reply back as text.
  • Start a new chat for each task.
  • Find and reopen earlier conversations.
  • Attach files to a prompt.
  • Pick a model. The default is Veo 3.1.
  • Tell you when the chat app is signed out.

Example

terminal
$ bridge ask --provider flow "Review this migration"

MCP tools for Google Flow

  • flow_generate: Generate a Veo clip from a Start keyframe image + a shot prompt (image-to-video), then download the mp4.
  • flow_list_clips: List the rendered clips in the current Flow project (id + mp4 URL).
  • flow_list_projects: List the Flow projects in the sidebar (id + title + URL).
  • flow_download_clips: Download clip mp4s to the target repo's .bridge/downloads/flow directory (all clips, or the given clipIds).
  • flow_delete_clip: Move a clip to Flow's recoverable Trash (requires confirm:true).
  • flow_rename_clip: Rename a clip.
  • flow_extend_clip: Add a clip to a scene (Flow's 'Add to scene' / extend).
  • flow_reuse_clip: Add a clip back to the prompt as input ('Add to prompt').
  • flow_rename_project: Rename the current Flow project.
  • flow_delete_project: Permanently delete the current Flow project (requires confirm:true; not a Trash move).
  • flow_list_ingredients: List the reference images (ingredients) attached to the current prompt.
  • flow_remove_ingredient: Detach one ingredient from the current prompt.
  • flow_clear_ingredients: Detach every ingredient from the current prompt.

Google Flow support

The bridge can also drive Google Labs Flow, Google's Veo-powered AI video studio, with the same Playwright/CDP pattern. Flow is different in kind from the chat providers: it is a generation surface, so a "reply" is a rendered clip and attachments are ingredients (reference images).

bridge chrome start --provider flow    # sign in to Google; account needs Flow access (AI Pro/Ultra)
bridge ask --provider flow "a cat surfing a neon wave, cinematic, 8s"
bridge ask --provider flow "same scene, dawn light" --attach ref1.png ref2.png   # up to 3 ingredients

Beyond generating, the bridge drives Flow's full asset lifecycle through bridge flow subcommands (each attaches to your current Flow project tab; add --json for machine-readable output):

bridge flow clips                        # list clips in the current project (id + fetchable URL)
bridge flow download                     # download every clip's mp4 to <repo>/.bridge/downloads/flow
bridge flow reuse   --id <clipId>        # add a clip back to the prompt as input ("Add to prompt")
bridge flow extend  --id <clipId>        # add a clip to a scene (Flow's "Add to scene")
bridge flow rename  --id <clipId> --name "hero shot"
bridge flow delete  --id <clipId> --yes  # move a clip to Flow Trash (recoverable)
bridge flow ingredients                  # list reference images attached to the prompt
bridge flow ingredient-remove --id <mediaId>   # detach one ingredient
bridge flow ingredient-clear             # detach every ingredient
bridge flow projects                     # list projects
bridge flow project-rename --name "Launch teaser"
bridge flow project-delete --yes         # permanently delete the current project

Destructive verbs (delete, project-delete) require --yes; clip delete moves to Flow's recoverable Trash.

Agents without shell access get the same lifecycle as flow_* MCP tools over bridge serve: flow_list_clips, flow_download_clips, flow_reuse_clip, flow_extend_clip, flow_rename_clip, flow_delete_clip, flow_list_ingredients, flow_remove_ingredient, flow_clear_ingredients, flow_list_projects, flow_rename_project, flow_delete_project. Destructive tools (flow_delete_clip, flow_delete_project) require confirm: true.

What works on Flow

  • Terminal-driven shot prompts that trigger Veo generation
  • Ingredients: attach up to three reference images to a prompt, and list / remove / clear already-attached ones
  • A captured clip reference (video src / download href) returned as the reply, so an agent gets a pointer to the result
  • Asset CRUD: list / download / rename / delete clips, extend or reuse a clip, manage prompt ingredients, and list / rename / delete projects, as bridge flow ... CLI commands and flow_* MCP tools over bridge serve
  • Reuses the same shared bridge profile / debug-port model as every provider

What does not work on Flow (today)

  • MCP connector, /task, /connector, /mcp: Flow has no connector UI, so the MCP server and Cloudflare tunnel are skipped (same as Gemini).
  • Stop / mid-render controls: cancelling a Veo render in flight is not wired yet.

Flow requires a Google AI Pro/Ultra plan. Because Veo renders take minutes, --provider flow waits far longer for a response than the chat providers do.

Selector maintenance: Flow's selectors were LIVE-VERIFIED against a signed-in project editor. If Google changes the UI, recapture with node scripts/dev/captureProviderSelectors.mjs, then update src/config.ts; generation lives in src/providers/flow/flow-page.ts and asset CRUD in src/providers/flow/flow-assets.ts.

Install

terminalinstall
you@mac ~ %PS C:\Users\you>you@ubuntu:~$ npm install -g ai-browser-bridge