browser_act
Perform one UI action. action ∈ click | double_click | right_click | type | clear | press_key | scroll | hover | wait | upload_file | select_option | navigate. target = element text/selector/coords; value = text/key/url/file-path.
This record as markdown: /tools/flowdot-llc-mcp-server/browser-act.md
What browser_act does on FlowDot MCP Server
AI agents call browser_act to permanently remove resources in FlowDot MCP Server, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why browser_act is rated Critical
An AI agent that decides to call browser_act doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from FlowDot MCP Server is gone. There is no undo for destructive operations.
Attacks that exploit this kind of access
The rule that runs browser_act safely
PolicyLayer is an MCP gateway: it sits between your AI agents and FlowDot MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For browser_act, this is the rule to start with:
browser_act is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect FlowDot MCP Server, apply this rule, and every browser_act call is checked against it from then on.
Questions about browser_act
Perform one UI action. action ∈ click | double_click | right_click | type | clear | press_key | scroll | hover | wait | upload_file | select_option | navigate. target = element text/selector/coords; value = text/key/url/file-path. It is categorised as a Destructive tool in the FlowDot MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the FlowDot MCP Server MCP server in PolicyLayer and add a rule for browser_act: 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 FlowDot MCP Server. Nothing to install.
browser_act is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the browser_act 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 browser_act. 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.
browser_act is provided by the FlowDot MCP Server MCP server (flowdot-llc/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on FlowDot MCP Server, and thousands of servers like it.
Across the catalogue