// SCAN REPORT

Mcp Browser Use

19 tools. 16 can modify or destroy data without limits.

16 write tools that can modify data. Rate limits recommended.

Last updated: 11 Jun 2026

16 can modify or destroy data

3 read-only

19 tools total

Community server · catalogue entry verified 11/06/2026

How to control Mcp Browser Use ↓

TOOL MAP

Read (3) Write / Execute (16) Destructive / Financial (0)

MOST DANGEROUS TOOLS

High Risk

Execute · High initialize_browser This tool launches a browser automation engine capable of arbitrary web interactions. Execute · Low wait The wait function executes code (a timer/sleep operation) and could be chained with other browser actions to create timed sequences or timing-based attacks. Execute · High click_element Clicking browser elements can trigger a wide range of external operations: submitting forms, initiating downloads, navigating pages, activating purchases, or executing JavaScript handlers. Execute · Medium go_back This tool performs a browser navigation action (equivalent to pressing the browser back button), which is an external operation that changes the browser state.

16 of Mcp Browser Use's 19 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

HOW TO CONTROL MCP BROWSER USE

PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Browser Use, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "close_browser": {
    "limits": [
      {
        "counter": "close_browser_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_dropdown_options": {
    "limits": [
      {
        "counter": "get_dropdown_options_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Mcp Browser Use — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON MCP BROWSER USE →

Free to start. No card required.

ALL 19 MCP BROWSER USE TOOLS

EXECUTE 14 tools

Execute initialize_browser Initialize a new browser instance. Args: headless: Whether to run browser in headless mode Execute wait Wait for the specified number of seconds. Args: seconds (int, optional): Number of seconds to wait Execute search_google Search the query in Google in the current tab. Args: query (str): The search query to use in Googl Execute click_element Click the element with the specified index. Args: index (int): The index of the element to click Execute go_back Go back to the previous page. Returns: str: A message confirming navigation back Execute go_to_url Navigate to URL in the current tab. Args: url (str): The URL to navigate to Returns: s Execute input_text Input text into an interactive element at the specified index. Args: index (int): The index of the Execute open_tab Open a URL in a new tab. Args: url (str): The URL to open in the new tab Returns: str: Execute scroll_down Scroll down the page by the specified amount. Args: amount (int, optional): Pixels to scroll down. Execute scroll_to_text Scroll to an element containing the specified text. Args: text (str): The text to find and scroll Execute scroll_up Scroll up the page by the specified amount. Args: amount (int, optional): Pixels to scroll up. If Execute select_dropdown_option Select an option from a dropdown by its text. Args: index (int): The index of the dropdown element Execute send_keys send_keys Execute switch_tab Switch to the tab with the specified page ID. Args: page_id (int): The ID of the page to switch to

WRITE 2 tools

Write close_browser Close the current browser instance. Returns: Status message Write done Complete the task with a success flag and optional text. Returns: dict: A dictionary indicating co

READ 3 tools

Read get_dropdown_options Get all options from a dropdown element. Args: index (int): The index of the dropdown element. Read inspect_page Lists interactive elements and extracts content from the current page. Returns: str: A formatted s Read validate_page Validate the current page state by extracting content and optionally checking for expected text. Args:

RELATED SERVERS

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

How do I prevent bulk modifications through Mcp Browser Use? +

The Mcp Browser Use server has 2 write tools including close_browser, done. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Mcp Browser Use.

How many tools does the Mcp Browser Use MCP server expose? +

19 tools across 3 categories: Execute, Read, Write. 3 are read-only. 16 can modify, create, or delete data.

How do I enforce a policy on Mcp Browser Use? +

Register the Mcp Browser Use MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Mcp Browser Use tool call.

Deterministic rules across all 19 Mcp Browser Use tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP BROWSER USE →

Free to start. No card required.

19 Mcp Browser Use tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

Mcp Browser Use

// TOOL MAP

// MOST DANGEROUS TOOLS

// HOW TO CONTROL MCP BROWSER USE

// ALL 19 MCP BROWSER USE TOOLS

// RELATED SERVERS

// FAQ