// SCAN REPORT

WebControl

20 tools. 10 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 2 Jul 2026

10 can modify or destroy data

10 read-only

20 tools total

Community server · catalogue entry verified 02/07/2026

How to control WebControl ↓

TOOL MAP

What WebControl exposes to your agents

Read (10) Write / Execute (9) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous WebControl tools

Destructive · Medium clear_network_capture Clearing captured network data is an irreversible operation; once the XHR/fetch responses are purged, that forensic/diagnostic information is gone. Execute · High execute_js This tool allows arbitrary code execution within a browser session. Execute · High navigate Navigate on a browser automation platform is an Execute action: it triggers external operations (page loads, script execution, network requests) whose effects depend on the target URL and page behavior. Execute · High click Clicking is a browser action whose consequences are determined by the target element at runtime.

10 of WebControl's 20 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control WebControl

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

Deny destructive operations

{
  "clear_network_capture": {
    "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

{
  "close_session": {
    "limits": [
      {
        "counter": "close_session_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "extract": {
    "limits": [
      {
        "counter": "extract_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 WebControl — 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 WEBCONTROL →

Instant setup, no code required.

FULL CATALOGUE

All 20 WebControl tools

DESTRUCTIVE 1 tools

Destructive clear_network_capture Clear the captured XHR/fetch responses for a session.

EXECUTE 8 tools

Execute click Click an element by its ref ID (from get_page_content). Returns updated page content. Execute configure_network_capture configure_network_capture Execute create_session Create a new browser session with isolated cookies and storage. Set enable_tracing=true to record a Playwright Execute execute_js Execute JavaScript on the current page. Returns updated page content. Execute fill Fill a form field by its ref ID with the given value. Returns updated page content. Execute navigate navigate Execute select Select a dropdown option by its ref ID. Value can be option text or value. Returns updated page content. Execute submit Submit a form by its ref ID (form element or submit button). Returns updated page content.

WRITE 1 tools

Write close_session Close a browser session and release its resources.

READ 10 tools

Read extract extract Read get_accessibility_tree Get the page's ARIA snapshot (accessibility tree as YAML). An Read get_html Get the full rendered HTML of the current page (truncated to a configured Read get_network_capture get_network_capture Read get_page_content Get the current page content with interactive element refs without performing any action. Read get_session_activity Get the action history for a session. Shows what actions were performed, their timing, and success/failure. Read get_session_stats Get performance statistics for a session: total actions, success/error counts, avg/min/max duration. Read list_sessions List all active browser sessions. Read screenshot Take a screenshot of the current page. Returns base64-encoded PNG. Read search search

EXPLORE

Related servers

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

FAQ

Questions about WebControl

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

Yes. The WebControl server exposes 1 destructive tools including clear_network_capture. 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 WebControl? +

The WebControl server has 1 write tools including close_session. 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 WebControl.

How many tools does the WebControl MCP server expose? +

20 tools across 4 categories: Destructive, Execute, Read, Write. 10 are read-only. 10 can modify, create, or delete data.

How do I enforce a policy on WebControl? +

Register the WebControl 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 WebControl tool call.

Deterministic rules across all 20 WebControl tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON WEBCONTROL →

Instant setup, no code required.

20 WebControl tools catalogued and risk-classified — across an index of 43,000+ MCP servers.