flow_connect

THE RISK

High Risk

Why flow_connect needs a policy

This tool launches a browser process, connects via Chrome DevTools Protocol (CDP), and navigates to an external web service. These are external operations (process execution, browser automation) whose effects depend on the configured profile and environment. No data is deleted or money moved, but it triggers real-world browser execution and external navigation, placing it in the Execute category.

From the tool's definition Launch Chrome with the configured Google profile, connect CDP, navigate to Google Flow, and verify account

Documented attack patterns abuse exactly the kind of access flow_connect gives an agent:

POLICY

How to control flow_connect

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_connect:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "flow_connect": {
      "limits": [
        {
          "counter": "flow_connect_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

flow_connect 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.

Create a free account and register Google Flow Browser MCP — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Google Flow Browser MCP tools

Financial flow_generate_image ⚠️ CES IMAGES CONSOMMENT DES CRÉDITS. Par défaut (auto_confirm=false): remplit le prompt, Execute flow_disconnect Close the browser and clean up the MCP connection to Google Flow. Execute flow_discover_ui Navigate to a Google Flow page and discover all interactive elements (buttons, inputs, lin Execute flow_generate_video Set up a video generation in Google Flow. Fills prompt, selects Omni Flash or Veo model, c Execute flow_use_grid_architect Open Grid Architect in Google Flow, fill theme prompt, shot prompts, engine, ratio, and vi Execute flow_use_tool Open any tool by name in Google Flow and optionally fill its configuration parameters. Write flow_create_character Create a new character in Google Flow Characters with name and description. Write flow_create_scene Create a new scene in Google Flow Scenes with characters and prompt.

All 17 Google Flow Browser MCP tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Google Flow Browser MCP → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about flow_connect

What does the flow_connect tool do? +

Launch Chrome with the configured Google profile, connect CDP, navigate to Google Flow, and verify account. 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.

How do I enforce a policy on flow_connect? +

Register the Google Flow Browser MCP server in PolicyLayer and add a rule for flow_connect: 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.

What risk level is flow_connect? +

flow_connect is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit flow_connect? +

Yes. Add a rate_limit block to the flow_connect 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.

How do I block flow_connect completely? +

Set action: deny in the PolicyLayer policy for flow_connect. 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.

What MCP server provides flow_connect? +

flow_connect 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.

Enforce policy on every Google Flow Browser MCP tool call.

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.

CHECK YOUR STACK →