List recent tasks with optional filtering. Args: limit: Maximum number of tasks to return (default 20) status_filter: Optional status filter (running, completed, failed) Returns: JSON list of recent tasks
AI agents call task_list to retrieve information from Browser-Use MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries task metadata without side effects. It presents data to the user but does not create, modify, delete, or execute operations. The blast radius is minimal—an AI agent querying recent tasks poses negligible security risk.
From the tool's definition Tool name 'task_list' and description 'List recent tasks with optional filtering' indicate a retrieval operation. Returns 'JSON list of recent tasks' with no mention of modification, deletion, or execution. Parameters are read-only (limit, status_filter).
Documented attack patterns abuse exactly the kind of access task_list gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Browser-Use MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for task_list:
{
"version": "1",
"default": "deny",
"tools": {
"task_list": {}
}
}task_list is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
List recent tasks with optional filtering. Args: limit: Maximum number of tasks to return (default 20) status_filter: Optional status filter (running, completed, failed) Returns: JSON list of recent tasks. It is categorised as a Read tool in the Browser-Use MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Browser-Use MCP Server MCP server in PolicyLayer and add a rule for task_list: 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 Browser-Use MCP Server. Nothing to install.
task_list is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the task_list 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 task_list. 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.
task_list is provided by the Browser-Use MCP Server MCP server (saik0s/mcp-browser-use). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 9 Browser-Use MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
9 Browser-Use MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.