Set up a video generation in Google Flow. Fills prompt, selects Omni Flash or Veo model, configures settings. NOTE: Does NOT click final Generate (paid feature — stops at ready-to-generate).
AI agents invoke flow_generate_video to trigger actions in Google Flow Browser MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool performs browser automation actions (filling forms, selecting models, configuring settings) that constitute external operations, placing it in Execute. It stops short of the final Generate click, which would be a Financial action, but the setup automation itself is an Execute-level action. Severity is medium because it stops before committing costs, but it does interact with an external paid service's UI.
From the tool's definition 'Set up a video generation in Google Flow. Fills prompt, selects Omni Flash or Veo model, configures settings.' and 'stops at ready-to-generate' — triggers browser automation actions (filling prompts, selecting models, configuring settings) without completing…
Documented attack patterns abuse exactly the kind of access flow_generate_video gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Google Flow Browser MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for flow_generate_video:
{
"version": "1",
"default": "deny",
"tools": {
"flow_generate_video": {
"limits": [
{
"counter": "flow_generate_video_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}flow_generate_video stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Set up a video generation in Google Flow. Fills prompt, selects Omni Flash or Veo model, configures settings. NOTE: Does NOT click final Generate (paid feature — stops at ready-to-generate). It is categorised as a Execute tool in the Google Flow Browser MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Google Flow Browser MCP server in PolicyLayer and add a rule for flow_generate_video: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Google Flow Browser MCP. Nothing to install.
flow_generate_video is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the flow_generate_video rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for flow_generate_video. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
flow_generate_video is provided by the Google Flow Browser MCP server (tmsss05/google-flow-browser-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Google Flow Browser MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
17 Google Flow Browser MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.