// SCAN REPORT

Fast Playwright MCP

34 tools. 26 can modify or destroy data without limits.

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

Last updated: 11 Jun 2026

26 can modify or destroy data

8 read-only

34 tools total

Community server · catalogue entry verified 11/06/2026

How to control Fast Playwright MCP ↓

TOOL MAP

Read (8) Write / Execute (25) Destructive / Financial (0)

MOST DANGEROUS TOOLS

High Risk

Execute · High browser_batch_execute This tool falls under Execute because it runs browser automation commands that produce real-world side effects (navigation, clicks, form submissions, file uploads, etc.) determined by the arguments provided. Execute · High browser_navigate Navigation is an Execute action: it runs a browser operation (navigation) that triggers external effects (fetching remote content, executing remote scripts, loading arbitrary web pages). Execute · Medium browser_navigate_back This tool executes a browser navigation action, which is an external operation that changes the state of the browser. Execute · Medium browser_navigate_forward While navigation itself is not inherently destructive, it executes a command with external effects (page state changes, potential script execution on target page, network requests).

26 of Fast Playwright MCP's 34 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

HOW TO CONTROL FAST PLAYWRIGHT MCP

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

Rate limit write operations

{
  "browser_close": {
    "limits": [
      {
        "counter": "browser_close_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "browser_find_elements": {
    "limits": [
      {
        "counter": "browser_find_elements_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 Fast Playwright MCP — 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 FAST PLAYWRIGHT →

Free to start. No card required.

ALL 34 FAST PLAYWRIGHT MCP TOOLS

EXECUTE 21 tools

Execute browser_batch_execute Execute multiple browser actions in sequence. PREFER over individual tools for 2+ operations. Execute browser_navigate Navigate to a URL Execute browser_navigate_back Go back to previous page Execute browser_navigate_forward Go forward to next page Execute browser_tab_new Open a new tab Execute browser_wait_for Wait for text to appear or disappear or a specified time to pass Execute browser_click Perform click on web page Execute browser_drag Perform drag and drop between two elements Execute browser_evaluate Evaluate JavaScript expression on page or element and return result Execute browser_handle_dialog Handle a dialog (alert, confirm, prompt) Execute browser_hover Hover over element on page Execute browser_install Install the browser specified in the config. Call this if you get an error about the browser not being install Execute browser_mouse_click_xy Click at specific coordinates Execute browser_mouse_drag_xy Drag from one coordinate to another Execute browser_mouse_move_xy Move mouse to specific coordinates.Requires --caps=vision.x,y:coordinates.expectation:{includeSnapshot:false} Execute browser_perform Perform a task with the browser. It can click, type, export, capture screenshot, drag, hover, select options, Execute browser_press_key Press a key on the keyboard Execute browser_resize Resize the browser window Execute browser_select_option Select option in dropdown Execute browser_tab_select Select a tab by index Execute browser_type Type text into editable element

WRITE 4 tools

Write browser_close Close the page Write browser_file_upload Upload one or multiple files to file input Write browser_pdf_save Save page as PDF Write browser_tab_close Close a tab by index or close current tab

READ 8 tools

Read browser_find_elements Find elements on the page using multiple search criteria such as text, role, tag name, or attributes. Returns Read browser_inspect_html Extract and analyze HTML content from web pages with intelligent filtering and size control. Optimized for LLM Read browser_snapshot Take a snapshot of the browser to read what is on the page. Read browser_tab_list List browser tabs with titles and URLs Read browser_take_screenshot Take a screenshot of current page and return image data Read browser_console_messages Returns all console messages Read browser_diagnose Analyze page complexity and performance characteristics. Reports on: iframe count, DOM size, modal states, ele Read browser_network_requests Returns network requests since loading the page with optional filtering

OTHER 1 tools

Other done Call this tool when the task is complete.

RELATED SERVERS

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

FAQ

How do I prevent bulk modifications through Fast Playwright MCP? +

The Fast Playwright MCP server has 4 write tools including browser_close, browser_file_upload, browser_pdf_save. 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 Fast Playwright MCP.

How many tools does the Fast Playwright MCP server expose? +

34 tools across 3 categories: Execute, Read, Write. 8 are read-only. 26 can modify, create, or delete data.

How do I enforce a policy on Fast Playwright MCP? +

Register the Fast Playwright 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 Fast Playwright MCP tool call.

Deterministic rules across all 34 Fast Playwright MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON FAST PLAYWRIGHT →

Free to start. No card required.

34 Fast Playwright MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

Fast Playwright MCP

// TOOL MAP

// MOST DANGEROUS TOOLS

// HOW TO CONTROL FAST PLAYWRIGHT MCP

// ALL 34 FAST PLAYWRIGHT MCP TOOLS

// RELATED SERVERS

// FAQ