High-risk tools in Browser-Use MCP Server
3 of the 9 tools in Browser-Use MCP Server are classified as high risk. This page profiles those tools specifically, with recommended policy actions and the attack patterns that target them.
Every operation listed below is an action PolicyLayer recommends controlling at the transport layer. Open any tool to see the full profile, risk score, and YAML policy snippet.
Tools at high risk
-
task_cancelExecuteCancel a running browser agent or research task. Args: task_id: Task ID (full or prefix match) Returns: JSON with success status and message
-
run_browser_agentExecuteExecute a browser automation task using AI. EXECUTION MODE (default): - When skill_name is provided, hints are injected for efficient navigation. LEARNING MODE (le...
-
run_deep_researchExecuteExecute deep research on a topic with progress tracking. Args: topic: The research topic or question to investigate max_searches: Maximum number of web sear...
Attacks that target this class
High-risk tools in any server share these documented attack patterns. Each links to the full case and the defensive policy.