// SCAN REPORT

JS Reverse MCP

22 tools. 11 can modify or destroy data without limits.

2 destructive tools with no built-in limits. Policy required.

Last updated: 26 Jun 2026

11 can modify or destroy data

11 read-only

22 tools total

Community server · catalogue entry verified 26/06/2026

How to control JS Reverse MCP ↓

TOOL MAP

What JS Reverse MCP exposes to your agents

Read (11) Write / Execute (9) Destructive / Financial (2)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous JS Reverse MCP tools

Destructive · High clear_site_data Although the tool targets only the currently selected page and is framed as creating a 'clean replay environment,' clearing cookies is a destructive operation—the deleted state cannot be programmatically restored. Destructive · Medium remove_breakpoint Removing breakpoints, particularly all of them at once, is an irreversible action that destroys debugging state. Execute · High navigate_page While navigation itself does not delete data or move money, it is an Execute category tool because it triggers external browser operations whose effects depend on the supplied URL argument. Execute · High new_page This tool executes browser navigation and page loading operations whose effects (executing page scripts, loading resources, triggering network requests, running third-party code) depend entirely on the URL provided.

11 of JS Reverse MCP's 22 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control JS Reverse MCP

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

Deny destructive operations

{
  "clear_site_data": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "save_script_source": {
    "limits": [
      {
        "counter": "save_script_source_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_paused_info": {
    "limits": [
      {
        "counter": "get_paused_info_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 JS Reverse 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 JS REVERSE →

Instant setup, no code required.

FULL CATALOGUE

All 22 JS Reverse MCP tools

DESTRUCTIVE 2 tools

Destructive clear_site_data Clear browser state to create a clean replay environment for the currently selected page. This clears cookies Destructive remove_breakpoint Removes breakpoints. Pass breakpointId to remove a code breakpoint, url to remove an XHR breakpoint, or neithe

EXECUTE 7 tools

Execute navigate_page Navigates the currently selected page to a URL, or performs back/forward/reload navigation. This tool only nav Execute new_page Opens a browser page and navigates to the specified URL. If an existing about:blank startup tab is still avail Execute break_on_xhr Sets a breakpoint that triggers when an XHR/Fetch request URL contains the specified string. Execute evaluate_script Evaluate a JavaScript function inside the currently selected page. Returns the response as JSON so returned va Execute step Steps JavaScript execution. Use direction Execute pause_or_resume Toggles JavaScript execution. If paused, resumes execution. If running, requests a pause at the next JavaScrip Execute set_breakpoint_on_text Sets a breakpoint on specific code (function name, statement, etc.) by searching loaded scripts and automatica

WRITE 2 tools

Write save_script_source Saves the full source code of a JavaScript script to a local file. PREFERRED over get_script_source whenever y Write select_frame Lists all frames (including iframes) in the current page. Pass frameIdx to switch the execution context used b

READ 11 tools

Read get_paused_info Gets information about the current paused state including call stack, current location, and scope variables. U Read get_request_initiator Gets the JavaScript call stack that initiated a network request. This helps trace which code triggered an API Read get_script_source Gets a small snippet of a JavaScript script source by URL (recommended) or script ID. Supports line range (for Read get_websocket_messages Lists WebSocket connections or gets messages for a specific connection. Without wsid, lists all connections. W Read list_breakpoints Lists active code breakpoints and XHR/Fetch URL breakpoints in the current debugging session. Breakpoints are Read list_console_messages List all console messages for the currently selected page since the last navigation. Pass msgid to get a singl Read list_network_requests List network requests for the currently selected page. By default this includes requests retained from before Read list_scripts Lists all JavaScript scripts loaded in the current page. Returns script ID, URL, and source map information. U Read search_in_sources Searches for a string or regex pattern in all loaded JavaScript sources. Returns matching lines with script ID Read take_screenshot Take a screenshot of the currently selected page. By default captures the visible viewport; set fullPage=true Read select_page Lists all open pages in the browser. Pass pageIdx to select a page as context for future tool calls.

EXPLORE

Related servers

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

FAQ

Questions about JS Reverse MCP

Can an AI agent delete data through the JS Reverse MCP server? +

Yes. The JS Reverse MCP server exposes 2 destructive tools including clear_site_data, remove_breakpoint. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through JS Reverse MCP? +

The JS Reverse MCP server has 2 write tools including save_script_source, select_frame. 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 JS Reverse MCP.

How many tools does the JS Reverse MCP server expose? +

22 tools across 4 categories: Destructive, Execute, Read, Write. 11 are read-only. 11 can modify, create, or delete data.

How do I enforce a policy on JS Reverse MCP? +

Register the JS Reverse 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 JS Reverse MCP tool call.

Deterministic rules across all 22 JS Reverse MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON JS REVERSE →

Instant setup, no code required.

22 JS Reverse MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.